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

    Neuronpedia

    INDEX
    Explanations

    instances of the letters "gs" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ı
    -2.30
    İ
    -2.30
    ĥ
    -2.28
    ¿½
    -2.24
    Ĥ
    -2.19
    ¼
    -2.14
    ĸ´
    -2.10
    Ĭ
    -2.09
    Ħ
    -2.06
    ĭ
    -2.06
    POSITIVE LOGITS
    heet
    1.91
    port
    1.85
    loop
    1.81
    enos
    1.74
    argument
    1.73
    velt
    1.67
    chaft
    1.66
    grounds
    1.65
    iop
    1.64
    ios
    1.63
    Act Density 0.015%

    No Known Activations