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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "reported."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     lenker
    -0.83
    IsContent
    -0.73
    DrawerToggle
    -0.64
    теризу
    -0.63
    ⟬
    -0.62
    InjectAttribute
    -0.62
    ազմ
    -0.60
     otomatig
    -0.60
    Портал
    -0.59
    ználat
    -0.59
    POSITIVE LOGITS
    imei
    0.66
    inemann
    0.63
     scripted
    0.62
     Marlowe
    0.60
     scrip
    0.59
     CURIAM
    0.59
    StringWriter
    0.59
    pushFollow
    0.59
    zama
    0.55
    чал
    0.55
    Act Density 0.015%

    No Known Activations