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

    Neuronpedia

    INDEX
    Explanations

    words related to causing reactions or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agua
    -0.15
    ovel
    -0.15
     Weaver
    -0.15
    untas
    -0.15
    ongan
    -0.15
    ravel
    -0.15
    imes
    -0.14
    ạch
    -0.14
    ä½į
    -0.14
    imony
    -0.14
    POSITIVE LOGITS
    63
    0.17
    -response
    0.17
    znik
    0.15
    ivate
    0.15
    235
    0.15
     aba
    0.14
    ingly
    0.14
     conversation
    0.14
    .elapsed
    0.14
     dormant
    0.14
    Act Density 0.131%

    No Known Activations