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

    Neuronpedia

    INDEX
    Explanations

    numerical values separated by commas

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olson
    -0.75
     exha
    -0.66
    phal
    -0.65
     suspic
    -0.64
    tti
    -0.64
     reluct
    -0.62
    deen
    -0.61
    llular
    -0.60
    hell
    -0.60
    everal
    -0.59
    POSITIVE LOGITS
    00
    0.91
    -+
    0.77
    inen
    0.73
    raction
    0.73
    ulse
    0.71
    escription
    0.70
    arth
    0.68
    25
    0.68
    ort
    0.68
    01
    0.63
    Act Density 0.036%

    No Known Activations