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

    Neuronpedia

    INDEX
    Explanations

    terms related to people's level of interest or enthusiasm

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fail
    -0.68
     stacked
    -0.67
    hemy
    -0.63
    ework
    -0.63
     botched
    -0.60
    ania
    -0.58
     fabricated
    -0.57
     Saints
    -0.56
    nova
    -0.56
    orthodox
    -0.56
    POSITIVE LOGITS
    ately
    0.73
    enza
    0.69
    ãĥĦ
    0.68
    atile
    0.68
     interested
    0.67
    iotics
    0.66
    ATIVE
    0.66
    rers
    0.66
    inery
    0.65
    ENC
    0.65
    Act Density 0.021%

    No Known Activations