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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Speaking."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kæ
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    ımı
    -0.53
     jadx
    -0.53
     orgull
    -0.52
    Klik
    -0.49
    }></
    -0.49
    DoubleQuotes
    -0.49
     Lyman
    -0.48
    '][$
    -0.48
    POSITIVE LOGITS
    Speaking
    1.35
     Speaking
    1.35
    speaking
    1.10
     speaking
    1.02
    出
    0.89
    談社
    0.67
     parlant
    0.66
     lest
    0.66
    出了
    0.66
     contextLoads
    0.62
    Act Density 0.077%

    No Known Activations