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

    Neuronpedia

    INDEX
    Explanations

    phrases related to initiating actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to launching or initiating actions or campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     someday
    -0.77
     conqu
    -0.73
    SPONSORED
    -0.73
     Niet
    -0.70
    ··
    -0.69
    Bee
    -0.68
    Eventually
    -0.67
    MJ
    -0.67
    Newsletter
    -0.65
     contrace
    -0.64
    POSITIVE LOGITS
    CLUS
    0.72
    oxide
    0.66
     crowdfunding
    0.65
     APP
    0.65
    zbollah
    0.64
    avering
    0.63
    EMA
    0.63
    ULL
    0.62
    cedented
    0.62
    itton
    0.62
    Act Density 0.340%

    No Known Activations