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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or actions related to deception or secrecy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     darm
    -0.16
    або
    -0.16
    herits
    -0.15
    .scalablytyped
    -0.15
    zas
    -0.15
    aven
    -0.15
     TextAlign
    -0.14
    zyst
    -0.14
    ernity
    -0.14
    lfw
    -0.14
    POSITIVE LOGITS
    kon
    0.16
    ascii
    0.15
    ows
    0.15
     ascii
    0.14
     низ
    0.14
     Virus
    0.14
    raquo
    0.14
     crossorigin
    0.14
    ddy
    0.14
    uya
    0.13
    Act Density 0.126%

    No Known Activations