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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating validation or evidence of claims or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vice
    -0.17
    olt
    -0.16
    ovan
    -0.15
    åį
    -0.15
    asurement
    -0.14
     Gems
    -0.14
    entiful
    -0.14
    ozor
    -0.14
    bum
    -0.14
    TRS
    -0.14
    POSITIVE LOGITS
    ırak
    0.17
     Tobacco
    0.15
    atten
    0.15
    éį
    0.15
    igm
    0.15
    icast
    0.14
    esz
    0.14
    IVO
    0.14
    hei
    0.14
     Spl
    0.13
    Act Density 0.167%

    No Known Activations