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

    Neuronpedia

    INDEX
    Explanations

    references to status, processes, or operations within a system

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     estekak
    -0.48
    </i>
    -0.47
    ).—
    -0.46
    ธอ
    -0.46
    nalités
    -0.45
     Cupcakes
    -0.45
     honom
    -0.44
     sauvegarde
    -0.44
    auen
    -0.43
    Демографія
    -0.43
    POSITIVE LOGITS
     also
    0.84
     meanwhile
    0.81
     تانيه
    0.73
     andererseits
    0.73
    also
    0.71
    autre
    0.71
     كذلك
    0.71
    SourceChecksum
    0.71
     another
    0.70
     lastly
    0.69
    Act Density 8.541%

    No Known Activations