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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deterring or discouraging something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "det" or its variations related to different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -1.02
    intendent
    -0.83
    manship
    -0.79
     nomine
    -0.73
     Awakens
    -0.72
    ammy
    -0.69
    BSD
    -0.68
    ħĭ
    -0.67
    externalActionCode
    -0.64
    raviolet
    -0.62
    POSITIVE LOGITS
    ention
    1.12
    achable
    1.05
    rans
    1.02
    ailed
    1.02
    roit
    1.02
    rend
    1.00
    ourn
    0.90
    rast
    0.89
    ainer
    0.88
    ried
    0.88
    Act Density 0.013%

    No Known Activations