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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "follow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folios
    -0.15
    itler
    -0.15
    dech
    -0.15
    ãĥ«ãĥķ
    -0.14
    uebas
    -0.14
     наб
    -0.14
    atures
    -0.14
    serialization
    -0.14
    arts
    -0.14
    ros
    -0.14
    POSITIVE LOGITS
    deen
    0.16
    stone
    0.15
    ç°
    0.14
    ystack
    0.14
    æĹ
    0.14
    bus
    0.14
    box
    0.14
    endoza
    0.14
    ýt
    0.13
     gerade
    0.13
    Act Density 0.026%

    No Known Activations