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

    Neuronpedia

    INDEX
    Explanations

    multiple instances of the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isia
    -0.16
    ĸ
    -0.15
    以为
    -0.14
    mq
    -0.14
    ipl
    -0.14
    εÏĤ
    -0.14
    Ñĥж
    -0.13
    ancel
    -0.13
    _LICENSE
    -0.13
    .AutoScaleMode
    -0.13
    POSITIVE LOGITS
    abra
    0.16
    115
    0.15
     trou
    0.14
    ohl
    0.14
    cribed
    0.14
    azen
    0.13
     untranslated
    0.13
    redo
    0.13
     ifndef
    0.13
    116
    0.13
    Act Density 0.080%

    No Known Activations