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

    Neuronpedia

    INDEX
    Explanations

    references to conflicts of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukes
    -0.16
    readcr
    -0.15
    ktion
    -0.15
    alian
    -0.14
    IDEO
    -0.14
    å·»
    -0.14
    Wrapped
    -0.14
    ÑģÑĤин
    -0.14
    WithTag
    -0.14
    _cpp
    -0.14
    POSITIVE LOGITS
     dil
    0.17
     crow
    0.16
     astr
    0.15
     o
    0.15
    ippi
    0.15
     diluted
    0.15
     Dil
    0.15
    heel
    0.14
    ircraft
    0.14
     relativ
    0.14
    Act Density 0.017%

    No Known Activations