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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.56
    ligente
    -0.54
     sedimentation
    -0.53
    رشف
    -0.52
    attaa
    -0.51
     siglos
    -0.51
     Lug
    -0.51
    attn
    -0.51
     tende
    -0.49
     Aene
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.78
     дописавши
    0.76
     AssemblyVersion
    0.70
     autorytatywna
    0.67
    \}\\
    0.60
     ModelExpression
    0.59
    PerformLayout
    0.58
    hyrchwyd
    0.58
    ConstraintMaker
    0.57
    oa̍t
    0.57
    Act Density 0.230%

    No Known Activations