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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities and investigations

    oai_token-act-pair · gpt-3.5-turbo

    the word "after" appearing frequently in contexts indicating chronological sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tick
    -0.86
    aez
    -0.82
    DragonMagazine
    -0.78
    oho
    -0.75
    ãĥ³ãĤ¸
    -0.75
    et
    -0.74
    Í
    -0.73
    isible
    -0.73
    ety
    -0.72
    obyl
    -0.71
    POSITIVE LOGITS
     discovering
    1.16
     noticing
    1.08
     receiving
    1.05
     completing
    1.01
     admitting
    0.99
     obtaining
    0.98
     spotting
    0.98
     failing
    0.97
     refusing
    0.96
     defeating
    0.95
    Act Density 0.112%

    No Known Activations