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

    Neuronpedia

    INDEX
    Explanations

    words related to branding and promotion

    oai_token-act-pair · gpt-3.5-turbo

    active verbs related to growth or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wives
    -0.63
    OPLE
    -0.62
    GET
    -0.60
     reper
    -0.58
    byn
    -0.57
    FORE
    -0.54
     Instr
    -0.53
     Haram
    -0.53
     Harbour
    -0.53
     posit
    -0.53
    POSITIVE LOGITS
    ed
    3.23
    edly
    2.12
    ing
    1.95
    edIn
    1.80
    ED
    1.79
    ered
    1.64
    eds
    1.52
    ioned
    1.36
    ned
    1.34
    ated
    1.28
    Act Density 0.365%

    No Known Activations