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

    Neuronpedia

    INDEX
    Explanations

    situations or actions involving unexpected or sudden events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the lack of consent or authorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    helle
    -0.72
     Christy
    -0.65
    oret
    -0.65
    nai
    -0.65
    agra
    -0.64
     LL
    -0.60
    olic
    -0.59
    roller
    -0.59
     Klux
    -0.59
    oir
    -0.59
    POSITIVE LOGITS
     whatsoever
    1.27
     interruption
    0.77
     nor
    0.76
     anymore
    0.73
     provocation
    0.72
    dding
    0.71
    fulness
    0.68
    pection
    0.65
     deductions
    0.65
     bloodshed
    0.64
    Act Density 0.091%

    No Known Activations