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

    Neuronpedia

    INDEX
    Explanations

    numerical values that are part of a structured data format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     murmuring
    -0.54
     quivering
    -0.51
     clatter
    -0.51
     vainly
    -0.48
     berea
    -0.48
     chattering
    -0.47
    squareup
    -0.46
     Gaetano
    -0.45
    ftagPool
    -0.45
     Cruces
    -0.45
    POSITIVE LOGITS
     gmbh
    0.95
     lapto
    0.86
     apparti
    0.85
     Luglio
    0.82
     €/
    0.82
     strass
    0.79
     marte
    0.79
     sappi
    0.78
     affatto
    0.78
    noinspection
    0.77
    Act Density 0.064%

    No Known Activations