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

    Neuronpedia

    INDEX
    Explanations

    words related to registration processes or documents

    oai_token-act-pair · gpt-3.5-turbo

    registration-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilk
    -0.76
    ITE
    -0.75
     flourish
    -0.72
    ittens
    -0.71
     handshake
    -0.70
    utherford
    -0.70
    uble
    -0.70
    essage
    -0.69
     Interstellar
    -0.68
    代
    -0.68
    POSITIVE LOGITS
    rants
    1.11
    rant
    1.07
    rar
    0.96
    ewater
    0.95
    rance
    0.95
    rator
    0.93
    ep
    0.91
    rage
    0.90
    rations
    0.89
    rary
    0.88
    Act Density 0.024%

    No Known Activations