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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "final" and its variations, indicating a focus on culminations or endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pery
    -0.20
    eping
    -0.14
    lets
    -0.14
    agas
    -0.14
    íĥĿ
    -0.14
    lifting
    -0.14
     пеÑĢв
    -0.14
    orgen
    -0.14
    eso
    -0.13
    ког
    -0.13
    POSITIVE LOGITS
    ity
    0.33
    ised
    0.32
    ization
    0.31
    izing
    0.29
    mente
    0.29
     touches
    0.27
    izes
    0.27
    ize
    0.27
    cial
    0.26
    ized
    0.25
    Act Density 0.028%

    No Known Activations