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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etu
    -0.16
    idlo
    -0.15
    erland
    -0.15
    -*-
    -0.14
    heimer
    -0.14
    دÙĬد
    -0.14
    lope
    -0.14
    daq
    -0.13
    isel
    -0.13
     Christine
    -0.13
    POSITIVE LOGITS
     bars
    0.14
    olicit
    0.14
     Bars
    0.14
     sublicense
    0.14
    åī¯
    0.14
    yal
    0.13
    REDIENT
    0.13
    á»iji
    0.13
    EG
    0.13
    313
    0.13
    Act Density 0.263%

    No Known Activations