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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "spot," particularly in contexts related to positioning or evaluating conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hir
    -0.18
    hat
    -0.18
    hm
    -0.18
    hu
    -0.17
    hor
    -0.17
    hay
    -0.17
    há
    -0.17
    ho
    -0.17
    hed
    -0.17
    hum
    -0.17
    POSITIVE LOGITS
    lights
    0.52
    light
    0.43
    ting
    0.41
    ter
    0.40
    LIGHT
    0.33
    lit
    0.32
    lessly
    0.30
    lite
    0.29
    tery
    0.29
    less
    0.28
    Act Density 0.013%

    No Known Activations