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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shape
    -0.87
     undecided
    -0.77
     likeness
    -0.77
     imagination
    -0.76
     unborn
    -0.76
     untouched
    -0.75
     unconscious
    -0.72
     unwanted
    -0.72
     independ
    -0.71
     ponder
    -0.70
    POSITIVE LOGITS
    ï¸ı
    1.00
    ï¸
    0.91
     Similarly
    0.86
    ttp
    0.86
    âĻ¦
    0.84
    However
    0.81
     Likewise
    0.81
    İ
    0.81
    tab
    0.81
     Previous
    0.81
    Act Density 0.210%

    No Known Activations