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

    Neuronpedia

    INDEX
    Explanations

    articles or news related to legal/criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "/" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prol
    -0.74
     onward
    -0.70
     creep
    -0.69
     shame
    -0.66
     hypnot
    -0.65
     melanch
    -0.64
     infertility
    -0.64
     overtime
    -0.63
     infiltr
    -0.63
     wrench
    -0.63
    POSITIVE LOGITS
    Charles
    1.24
    Marc
    1.23
    Susan
    1.21
    Eric
    1.15
    Rich
    1.14
    Las
    1.14
    Neil
    1.13
    Jac
    1.13
    David
    1.12
    Ted
    1.11
    Act Density 0.015%

    No Known Activations