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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or data points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erk
    -0.19
    itz
    -0.16
    .googlecode
    -0.15
    bic
    -0.15
    ed
    -0.15
    erie
    -0.14
    ubb
    -0.14
    еÑĤелÑĮ
    -0.14
    Ñħодим
    -0.14
    astro
    -0.14
    POSITIVE LOGITS
    ters
    0.20
    663
    0.18
    Û°Û°Û°
    0.17
    kker
    0.16
    0
    0.16
    uous
    0.15
    776
    0.15
    eneg
    0.15
    CTYPE
    0.14
    sock
    0.14
    Act Density 0.068%

    No Known Activations