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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "different" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inee
    -0.15
    inous
    -0.15
    ouble
    -0.14
    ло
    -0.14
    abei
    -0.14
    awei
    -0.14
    arken
    -0.14
    setImage
    -0.14
    коÑģÑĤÑĮ
    -0.14
    .cg
    -0.14
    POSITIVE LOGITS
    iating
    0.52
    iator
    0.42
    iable
    0.40
    iates
    0.40
    ially
    0.37
    iators
    0.36
    iability
    0.33
    iations
    0.33
    ials
    0.32
    iate
    0.30
    Act Density 0.056%

    No Known Activations