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

    Neuronpedia

    INDEX
    Explanations

    keywords related to the media

    oai_token-act-pair · gpt-3.5-turbo

    references to the media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pis
    -0.72
    vasive
    -0.70
    ranged
    -0.69
    ta
    -0.69
    combe
    -0.69
    sql
    -0.68
    oku
    -0.68
    0000000000000000
    -0.67
    İĭ
    -0.67
    cair
    -0.66
    POSITIVE LOGITS
    eval
    1.39
     outlets
    1.25
     outlet
    1.09
     coverage
    1.07
     mogul
    0.99
     circus
    0.96
     portrayal
    0.94
     pundits
    0.91
     mog
    0.91
     blackout
    0.89
    Act Density 0.049%

    No Known Activations