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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric values or programming structure elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enal
    -0.16
    ess
    -0.16
     bund
    -0.15
     Helmet
    -0.14
    agal
    -0.14
    Helmet
    -0.14
    966
    -0.14
    ãĤĬ
    -0.13
     Snape
    -0.13
    ses
    -0.13
    POSITIVE LOGITS
     Cum
    0.16
     ê
    0.16
    VERTISEMENT
    0.15
    /jav
    0.15
    Cum
    0.14
    abor
    0.14
    CLUD
    0.14
    rez
    0.14
    acob
    0.14
    stice
    0.13
    Act Density 0.083%

    No Known Activations