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

    Neuronpedia

    INDEX
    Explanations

    action verbs that indicate creation, performance, or processes involving change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tal
    -0.69
    B
    -0.57
    be
    -0.56
    ec
    -0.55
    t
    -0.55
    ton
    -0.54
    P
    -0.54
    pr
    -0.54
    to
    -0.54
    ph
    -0.53
    POSITIVE LOGITS
    ')")
    1.01
     itſelf
    0.94
    ']")
    0.92
     كومونز
    0.92
    )]:
    0.90
     дописавши
    0.90
    ']?>
    0.89
     }}-
    0.88
     Numerade
    0.88
    citenamefont
    0.87
    Act Density 0.546%

    No Known Activations