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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "mod" indicating modifications or modeling in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lük
    -0.16
    alion
    -0.15
    ceptor
    -0.15
    ãĥ¼ãĥľ
    -0.15
     Creed
    -0.15
    Modifier
    -0.14
    ittest
    -0.14
    ombres
    -0.14
    ienie
    -0.14
    ancia
    -0.14
    POSITIVE LOGITS
    elling
    0.32
    ding
    0.31
    ded
    0.29
    esty
    0.29
    ality
    0.28
    ularity
    0.27
    ular
    0.27
    ulated
    0.27
    ifying
    0.26
    ifiable
    0.26
    Act Density 0.016%

    No Known Activations