Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical specifications or details related to programming or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation marks or specialized characters in technical documents that are often at the end of structured sections, measurements, or references, typically indicating the end of a data field, category, or parameter.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Negative Logits
    ()]);
    -0.33
     curto
    -0.32
     recul
    -0.32
    ţe
    -0.31
    esterno
    -0.31
    romo
    -0.30
     prequel
    -0.30
     backlash
    -0.30
    ()");
    -0.30
     Hinweise
    -0.30
    POSITIVE LOGITS
     nahilalakip
    0.66
    ſelf
    0.65
     ſtate
    0.59
    ſelves
    0.58
    addContainerGap
    0.57
     Houſe
    0.57
    RenderAtEndOf
    0.56
     houſe
    0.55
    //
    0.52
    AutoField
    0.52
    Act Density 0.339%

    No Known Activations