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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to philosophy and the human mind

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     carrefour
    -0.65
     couverte
    -0.53
     pamph
    -0.52
     végétal
    -0.52
    madeus
    -0.51
     Joaqu
    -0.49
     bourg
    -0.49
     ritard
    -0.49
     Sénégal
    -0.48
    undred
    -0.47
    POSITIVE LOGITS
     remainder
    0.60
     consists
    0.53
     ºC
    0.52
    remainder
    0.52
     consisting
    0.50
     reserved
    0.49
    °;
    0.49
     portion
    0.48
     comprises
    0.47
     separately
    0.47
    Act Density 0.475%

    No Known Activations