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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude or requesting assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udi
    -0.18
     (
    -0.13
    erosis
    -0.13
    ymm
    -0.13
     '
    -0.13
    inium
    -0.13
     Imaging
    -0.13
    iffin
    -0.13
    åĭ
    -0.13
    lien
    -0.13
    POSITIVE LOGITS
    ously
    0.15
    linky
    0.15
    ANGE
    0.14
     Clarkson
    0.14
    IRT
    0.14
    handleChange
    0.14
    ruba
    0.14
    chaft
    0.14
    heel
    0.13
    gence
    0.13
    Act Density 0.004%

    No Known Activations