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

    Neuronpedia

    INDEX
    Explanations

    references to film and television projects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reflex
    -0.88
     persuasion
    -0.83
     equival
    -0.81
     occasional
    -0.81
     agon
    -0.80
     unexplained
    -0.79
     habit
    -0.77
     torture
    -0.77
     bias
    -0.77
     naive
    -0.77
    POSITIVE LOGITS
    Tickets
    1.60
    Meanwhile
    1.48
    RELATED
    1.47
    Among
    1.47
    Also
    1.46
    According
    1.40
    Additionally
    1.38
    Along
    1.34
    Both
    1.33
    Speaking
    1.32
    Act Density 0.420%

    No Known Activations