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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Вікі
    -0.69
    unhofer
    -0.60
     Faso
    -0.59
    OCCURRED
    -0.59
    amaran
    -0.58
    orsese
    -0.57
    nologue
    -0.57
    tonsoft
    -0.57
    iciary
    -0.56
    coran
    -0.56
    POSITIVE LOGITS
    ardless
    0.56
     meta
    0.52
     erk
    0.52
    multicolumn
    0.51
    meta
    0.48
    IntoConstraints
    0.47
    ารถ
    0.46
     aware
    0.46
     campi
    0.45
     realize
    0.45
    Act Density 0.290%

    No Known Activations