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

    Neuronpedia

    INDEX
    Explanations

    references to "touch" and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idal
    -0.16
    iska
    -0.15
    anto
    -0.15
    quo
    -0.15
    ãn
    -0.15
    ivant
    -0.15
    ÑĪев
    -0.15
    -desc
    -0.14
    Ŀ
    -0.14
    issors
    -0.14
    POSITIVE LOGITS
    screens
    0.28
    stone
    0.26
    stones
    0.25
    pad
    0.24
    screen
    0.23
    UpInside
    0.23
    y
    0.23
    points
    0.22
    ingly
    0.21
    -screen
    0.20
    Act Density 0.016%

    No Known Activations