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

    Neuronpedia

    INDEX
    Explanations

    words related to the exploitation of animals for various purposes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pamph
    -0.96
     quitted
    -0.86
     apprehen
    -0.81
     reconno
    -0.81
     Moslem
    -0.72
     gaily
    -0.72
     Minang
    -0.71
     marcato
    -0.71
     Shakspeare
    -0.71
     shenan
    -0.70
    POSITIVE LOGITS
     szóci
    0.52
    annica
    0.49
     \%$\\
    0.46
     parfum
    0.45
    used
    0.44
    askets
    0.44
     dishes
    0.43
     salads
    0.43
     FUNERAL
    0.43
     used
    0.42
    Act Density 0.315%

    No Known Activations