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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal, political, and governmental issues

    oai_token-act-pair · gpt-3.5-turbo

    sentences that prominently feature the word "It" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.69
     decimal
    -0.65
     buds
    -0.64
     Slayer
    -0.63
    ¯
    -0.63
     bud
    -0.62
     transistor
    -0.62
     reef
    -0.60
     \"
    -0.59
     VR
    -0.59
    POSITIVE LOGITS
    resa
    1.28
    odore
    1.25
    ogether
    1.07
    romeda
    1.05
    alyst
    1.04
    withstanding
    1.02
    icularly
    1.00
    notations
    0.99
    theless
    0.97
    intendent
    0.97
    Act Density 0.762%

    No Known Activations