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

    Neuronpedia

    INDEX
    Explanations

    words related to legal matters and political activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifter
    -0.61
    adish
    -0.61
     Jou
    -0.60
    asp
    -0.56
    fare
    -0.54
    owler
    -0.53
    oufl
    -0.53
    stall
    -0.52
    dar
    -0.51
    asta
    -0.51
    POSITIVE LOGITS
     thereto
    1.38
     to
    1.08
    entious
    0.89
    To
    0.89
     unto
    0.84
    ences
    0.80
    to
    0.78
    TO
    0.76
    itiz
    0.76
    pires
    0.76
    Act Density 1.638%

    No Known Activations