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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or progress towards goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.18
    arring
    -0.15
    .ast
    -0.15
    enville
    -0.15
    olley
    -0.15
    ocache
    -0.15
    ocytes
    -0.15
    olls
    -0.14
    portun
    -0.14
    contrast
    -0.14
    POSITIVE LOGITS
    BV
    0.15
    sey
    0.14
    ëĵĿ
    0.14
    asca
    0.14
    ãģĹãģĭ
    0.14
    PLAIN
    0.14
    dam
    0.14
    YNC
    0.14
    Unsafe
    0.13
    PLICIT
    0.13
    Act Density 0.037%

    No Known Activations