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

    Neuronpedia

    INDEX
    Explanations

    mentions of SQL database queries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "from."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.82
    mun
    -0.82
    sylv
    -0.81
    erto
    -0.77
    idav
    -0.76
    faced
    -0.75
    bush
    -0.74
    webkit
    -0.73
    ilts
    -0.72
    irm
    -0.71
    POSITIVE LOGITS
     afar
    1.36
     whence
    1.14
     scratch
    1.09
     thence
    0.92
     abroad
    0.92
     anywhere
    0.92
     inception
    0.87
     Uni
    0.83
     within
    0.80
     inside
    0.79
    Act Density 0.141%

    No Known Activations