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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ceremonial standing ovations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to awards and commendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     schizophren
    -0.69
    hom
    -0.68
     endemic
    -0.67
    wal
    -0.64
    netflix
    -0.63
    inks
    -0.62
    thinking
    -0.62
    anth
    -0.62
     Fuk
    -0.61
    £ı
    -0.60
    POSITIVE LOGITS
    vation
    1.10
    onement
    0.83
    etheus
    0.78
    owment
    0.75
    ariat
    0.73
     oath
    0.69
    eer
    0.68
    ylon
    0.67
    ppelin
    0.66
     orchestra
    0.64
    Act Density 0.055%

    No Known Activations