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

    Neuronpedia

    INDEX
    Explanations

    words related to provocative or challenging actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to advocacy and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGTON
    -0.73
     Archdemon
    -0.69
    ĸļ
    -0.69
     Amen
    -0.68
     Attention
    -0.66
     Hats
    -0.64
     Done
    -0.63
     Beir
    -0.63
     737
    -0.63
     Instruments
    -0.63
    POSITIVE LOGITS
    ception
    1.11
    chnology
    1.08
    ffect
    1.01
    lect
    0.99
    ople
    0.98
    ce
    0.93
    cing
    0.91
    vious
    0.90
    urs
    0.90
    chn
    0.90
    Act Density 0.198%

    No Known Activations