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

    Neuronpedia

    INDEX
    Explanations

    references to different file formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jours
    -1.51
    itely
    -1.48
    unts
    -1.44
    §
    -1.36
     spite
    -1.35
    their
    -1.35
     vain
    -1.33
     wonders
    -1.33
    ---|---
    -1.32
     their
    -1.31
    POSITIVE LOGITS
    mith
    1.78
    ium
    1.78
     horizon
    1.71
    creen
    1.69
    ricular
    1.69
    chool
    1.67
    ensor
    1.63
    helf
    1.60
    icum
    1.60
    etting
    1.58
    Act Density 0.015%

    No Known Activations