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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "utter" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦÏģ
    -0.15
    .cum
    -0.15
    .Modules
    -0.15
    绾
    -0.14
     curs
    -0.14
    /Framework
    -0.14
    arella
    -0.14
     kas
    -0.14
     Curse
    -0.14
    ader
    -0.13
    POSITIVE LOGITS
    odox
    0.17
    airo
    0.15
    isti
    0.15
    isté
    0.15
    ty
    0.15
    ijkstra
    0.15
    ombine
    0.15
    ầm
    0.14
    ideon
    0.14
    ties
    0.14
    Act Density 0.012%

    No Known Activations