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

    Neuronpedia

    INDEX
    Explanations

    punctuation and dialogue markers, often indicative of speech or emotional expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.00
     Efq
    -0.94
     purpoſe
    -0.85
     houſe
    -0.84
     itſelf
    -0.84
     pleaſure
    -0.83
     ſtate
    -0.81
     Houſe
    -0.81
     myſelf
    -0.80
     becauſe
    -0.80
    POSITIVE LOGITS
     he
    0.84
     they
    0.69
     she
    0.69
     I
    0.67
     mumbled
    0.62
    IntoConstraints
    0.60
     The
    0.59
     They
    0.59
     He
    0.57
     <=",
    0.55
    Act Density 0.020%

    No Known Activations