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

    Neuronpedia

    INDEX
    Explanations

    A particular phrase requesting action or input from the reader, specifically involving email addresses or selections

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods, indicating the conclusion of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oun
    -0.80
     homebrew
    -0.79
    icum
    -0.70
     cod
    -0.69
     exploited
    -0.66
     idol
    -0.65
     imperson
    -0.65
     toler
    -0.65
     hunted
    -0.64
     paradox
    -0.63
    POSITIVE LOGITS
     Please
    0.92
    php
    0.87
    jpg
    0.83
    Repeat
    0.83
    dll
    0.81
     Your
    0.80
     Sorry
    0.80
    wav
    0.79
    ItemTracker
    0.77
    PsyNetMessage
    0.77
    Act Density 0.036%

    No Known Activations