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

    Neuronpedia

    INDEX
    Explanations

    references to comments and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yr
    -0.16
    ouz
    -0.16
    à¥ĩत
    -0.15
    yan
    -0.15
    impan
    -0.15
    quan
    -0.15
    emouth
    -0.14
    баÑĩ
    -0.14
    abet
    -0.14
    pel
    -0.14
    POSITIVE LOGITS
    aries
    0.34
    aires
    0.28
    luv
    0.28
    ariat
    0.25
    ators
    0.24
    ers
    0.24
    ary
    0.24
    aar
    0.22
    ative
    0.22
    arial
    0.22
    Act Density 0.039%

    No Known Activations