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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "ant."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ract
    -0.18
    Ùĩ
    -0.17
    ska
    -0.17
    rig
    -0.16
    rl
    -0.16
    ÛĮ
    -0.16
    iou
    -0.15
    s
    -0.15
    rch
    -0.15
    र
    -0.15
    POSITIVE LOGITS
    y
    0.33
    yne
    0.26
    ech
    0.25
    ucket
    0.25
    yre
    0.22
    yh
    0.22
    elope
    0.21
    ucky
    0.20
    rop
    0.20
    astic
    0.19
    Act Density 0.032%

    No Known Activations