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

    Neuronpedia

    INDEX
    Explanations

    sentences or clauses that indicate affirmation or assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agamemnon
    -0.73
    Personendaten
    -0.73
    хьтан
    -0.70
    География
    -0.67
    __(/*!
    -0.66
     Kalyan
    -0.64
     Molière
    -0.63
    Hilsen
    -0.63
     consuls
    -0.63
    Mutagenicity
    -0.62
    POSITIVE LOGITS
     possible
    1.15
     impossible
    1.03
    possible
    0.95
     raining
    0.91
     difficult
    0.91
     easier
    0.90
     easy
    0.86
     mogelijk
    0.82
     unclear
    0.81
     snowing
    0.80
    Act Density 0.637%

    No Known Activations