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

    Neuronpedia

    INDEX
    Explanations

    words related to modeling and modification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.17
    fully
    -0.17
    alion
    -0.16
    urious
    -0.15
     Perc
    -0.15
    ãĥ¼ãĥľ
    -0.15
     Hansen
    -0.15
    ienie
    -0.14
    atology
    -0.14
    ceptor
    -0.14
    POSITIVE LOGITS
    elling
    0.31
    ded
    0.31
    ding
    0.30
    ERN
    0.27
    ellers
    0.26
    ernity
    0.26
    ality
    0.25
    erna
    0.25
    ifiable
    0.24
    ularity
    0.24
    Act Density 0.018%

    No Known Activations