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

    Neuronpedia

    INDEX
    Explanations

    references to a command or statement calling for action or attention

    oai_token-act-pair · gpt-3.5-turbo

    periods and certain punctuation, particularly at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bum
    -0.64
    obin
    -0.61
    erity
    -0.61
     guiName
    -0.60
     signing
    -0.59
    aiman
    -0.58
    inka
    -0.57
     qualification
    -0.57
    dule
    -0.57
    iga
    -0.57
    POSITIVE LOGITS
    Reviewed
    0.80
    accompanied
    0.76
    uyomi
    0.66
    Introduced
    0.65
     Fem
    0.63
    Includes
    0.62
    endif
    0.61
    âĵĺ
    0.59
     Activate
    0.59
    taboola
    0.59
    Act Density 0.465%

    No Known Activations