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

    Neuronpedia

    INDEX
    Explanations

    references to the word "ant" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rint
    -0.17
    rl
    -0.17
    ryo
    -0.17
    ra
    -0.15
    lear
    -0.15
    trl
    -0.15
    opup
    -0.14
    baÅŁ
    -0.14
    र
    -0.14
    ru
    -0.14
    POSITIVE LOGITS
    ucket
    0.23
    woord
    0.20
    ropic
    0.20
    y
    0.19
    elope
    0.18
    yne
    0.18
    ucky
    0.18
    rop
    0.18
    enna
    0.17
    ing
    0.17
    Act Density 0.037%

    No Known Activations