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

    Neuronpedia

    INDEX
    Explanations

    terms related to spotlight or highlighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.19
    utom
    -0.16
    how
    -0.16
    ?action
    -0.15
    cla
    -0.15
    hari
    -0.15
    ालय
    -0.15
    slt
    -0.14
    ëĵĿ
    -0.14
    tainment
    -0.14
    POSITIVE LOGITS
    ting
    0.40
    lights
    0.38
    ter
    0.32
    aneous
    0.24
    spot
    0.24
    light
    0.23
    lessly
    0.23
    TERS
    0.22
    tery
    0.22
    aneously
    0.21
    Act Density 0.021%

    No Known Activations