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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with assessment and communication of capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.16
     saddle
    -0.14
    sonian
    -0.14
    串
    -0.14
     ãĥ»
    -0.13
    vention
    -0.13
    ê±°
    -0.13
    anela
    -0.13
    TokenType
    -0.13
    chop
    -0.13
    POSITIVE LOGITS
    otre
    0.20
     initially
    0.18
    ulton
    0.17
    initial
    0.16
    bai
    0.16
    Initially
    0.15
    ãģ¾ãģļ
    0.15
     Initially
    0.15
     Briggs
    0.15
     initial
    0.14
    Act Density 0.007%

    No Known Activations