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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulations, legal matters, and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    specific high-frequency symbols or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     likeness
    -0.83
     shape
    -0.79
     unconscious
    -0.77
     imagination
    -0.76
     resemblance
    -0.74
     scissors
    -0.73
     cradle
    -0.72
     untouched
    -0.71
     rune
    -0.71
     undecided
    -0.70
    POSITIVE LOGITS
    ï¸ı
    1.01
    VERTISEMENT
    0.89
    âĻ¦
    0.88
    ï¸
    0.86
    tab
    0.84
    ¯
    0.84
    İ
    0.83
    VII
    0.82
    âĸ
    0.82
    °
    0.80
    Act Density 0.228%

    No Known Activations