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

    Neuronpedia

    INDEX
    Explanations

    crime-related events or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey conclusive or summarizing statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fishes
    -0.76
     defe
    -0.75
    ŃĶ
    -0.71
     minion
    -0.69
     conserve
    -0.69
     regenerate
    -0.68
     pace
    -0.68
     unch
    -0.68
     volunte
    -0.66
     covenant
    -0.66
    POSITIVE LOGITS
     Similarly
    1.41
     Later
    1.27
     Likewise
    1.23
     Similar
    1.19
     Afterwards
    1.18
     Shortly
    1.15
     Another
    1.10
     Meanwhile
    1.09
     Ironically
    1.08
    Similarly
    1.05
    Act Density 0.583%

    No Known Activations