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

    Neuronpedia

    INDEX
    Explanations

    phrases related to imitation or imitation products

    oai_token-act-pair · gpt-3.5-turbo

    references to artificiality or imitation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edient
    -0.73
    ository
    -0.73
    llah
    -0.73
    omb
    -0.71
    ovo
    -0.70
    essa
    -0.70
    onent
    -0.70
    enance
    -0.69
    itute
    -0.69
     Hoffman
    -0.68
    POSITIVE LOGITS
     pas
    1.14
     faux
    0.99
    pas
    0.90
    hawk
    0.81
     lion
    0.74
    cus
    0.72
    cin
    0.70
     lam
    0.70
     fur
    0.68
     tan
    0.68
    Act Density 0.011%

    No Known Activations