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

    Neuronpedia

    INDEX
    Explanations

    mentions of a person named "Doc"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    craft
    -0.63
    Stars
    -0.62
     aspiration
    -0.61
    ATIVE
    -0.59
     tun
    -0.59
     brim
    -0.58
    ounter
    -0.57
    wa
    -0.57
    sembly
    -0.55
    éŃĶ
    -0.55
    POSITIVE LOGITS
    herty
    0.92
    zilla
    0.86
    enhagen
    0.84
    ious
    0.79
    igslist
    0.75
    emort
    0.75
    vous
    0.72
    ocamp
    0.72
    lers
    0.72
    osal
    0.71
    Act Density 0.128%

    No Known Activations