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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing preferences or lack of concern

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing indifference or lack of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.76
    reek
    -0.74
    EStreamFrame
    -0.73
    ULTS
    -0.71
    IB
    -0.70
    thumbnails
    -0.69
    ãĥ©ãĥ³
    -0.68
    é¾
    -0.68
    Avg
    -0.67
    /**
    -0.65
    POSITIVE LOGITS
    lessly
    1.10
    fully
    0.83
    fulness
    0.76
    atically
    0.69
    storms
    0.69
    otrop
    0.66
    achine
    0.65
    lessness
    0.63
    edly
    0.63
     uploading
    0.62
    Act Density 0.014%

    No Known Activations