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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mysterious events and phenomena

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to theories or speculation about mysterious events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emn
    -0.89
    emale
    -0.88
    olutely
    -0.85
    onomy
    -0.85
    ourse
    -0.83
    olute
    -0.81
    verages
    -0.81
    inguished
    -0.79
    orest
    -0.78
    estyles
    -0.77
    POSITIVE LOGITS
     somew
    1.43
     somewhere
    1.38
     somet
    1.21
     somehow
    1.17
     something
    1.06
     nefarious
    1.02
     somebody
    0.98
     maybe
    0.96
     Something
    0.95
    Something
    0.93
    Act Density 0.908%

    No Known Activations