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

    Neuronpedia

    INDEX
    Explanations

    sentences that indicate uncertainty or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.83
     Jefus
    -0.78
    StateToProps
    -0.75
     doings
    -0.74
     Diſ
    -0.72
    Empereur
    -0.69
    󠁢
    -0.68
     Monfieur
    -0.67
    =$?
    -0.67
     crap
    -0.65
    POSITIVE LOGITS
    Autoritní
    0.63
    EXCLUSIVE
    0.52
    annica
    0.52
    Personendaten
    0.51
     дописавши
    0.49
    MigrationBuilder
    0.47
     VIAF
    0.46
    sellors
    0.46
    richTextPanel
    0.45
    irical
    0.45
    Act Density 0.140%

    No Known Activations