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

    Neuronpedia

    INDEX
    Explanations

    numbers related to historical events and time periods

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rcParams
    -0.65
     alkoh
    -0.57
     pü
    -0.55
    ModelForm
    -0.54
    StartPosition
    -0.54
    PushButton
    -0.53
    WebControls
    -0.53
    Matchers
    -0.53
    Descripció
    -0.53
     optik
    -0.53
    POSITIVE LOGITS
     intersper
    1.03
     overcrow
    0.95
     apprehen
    0.92
     shenan
    0.84
     underval
    0.83
     stickied
    0.81
     unspeak
    0.80
     indestru
    0.78
     maneu
    0.78
     downvote
    0.78
    Act Density 0.158%

    No Known Activations