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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "touch" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idal
    -0.17
    quo
    -0.15
    ÑĪев
    -0.15
    ãĥ³ãĥĸ
    -0.15
    ÑĢава
    -0.15
    issors
    -0.15
    anto
    -0.14
    ntl
    -0.14
    uito
    -0.14
    isor
    -0.14
    POSITIVE LOGITS
    screens
    0.28
    screen
    0.24
    stone
    0.24
    stones
    0.23
    -screen
    0.23
    points
    0.23
    UpInside
    0.22
    pad
    0.22
    y
    0.21
    down
    0.20
    Act Density 0.017%

    No Known Activations