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

    Neuronpedia

    INDEX
    Explanations

    comparative terms indicating an increase or greater quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     authoritative
    -0.14
     Solid
    -0.14
    ti
    -0.13
     Schwarz
    -0.13
    ulls
    -0.13
    inform
    -0.13
    uls
    -0.13
    γγ
    -0.13
     hol
    -0.13
    tok
    -0.13
    POSITIVE LOGITS
    LEMENT
    0.16
    ocab
    0.16
    XHR
    0.15
    .gameserver
    0.15
    gue
    0.14
    erdale
    0.14
    inea
    0.14
    :frame
    0.14
    ëĮ
    0.14
    TRACE
    0.14
    Act Density 0.018%

    No Known Activations