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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "When" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aud
    -0.17
    veau
    -0.15
    voke
    -0.15
    cha
    -0.14
    ole
    -0.14
    React
    -0.14
     Pra
    -0.14
    ão
    -0.14
    vert
    -0.14
    arin
    -0.14
    POSITIVE LOGITS
     GOODMAN
    0.18
    OwnProperty
    0.16
    .openg
    0.15
    imilar
    0.14
    elage
    0.14
    paque
    0.14
    elter
    0.14
    rane
    0.13
    abouts
    0.13
    	TokenName
    0.13
    Act Density 0.040%

    No Known Activations