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

    Neuronpedia

    INDEX
    Explanations

    expressions of complaint or dissatisfaction

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "mean" and related derivatives indicating significance or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     packs
    -0.60
     circles
    -0.58
     Diesel
    -0.57
     Greenberg
    -0.56
     Axel
    -0.55
    icka
    -0.55
     Schwar
    -0.55
    kowski
    -0.53
     dynasty
    -0.52
     Tue
    -0.51
    POSITIVE LOGITS
    etheless
    1.29
    ishly
    1.01
    ighed
    1.00
    ITH
    0.98
    selves
    0.97
    ances
    0.93
    theless
    0.92
    FORE
    0.92
    ween
    0.91
    ciating
    0.91
    Act Density 0.203%

    No Known Activations