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

    Neuronpedia

    INDEX
    Explanations

    negations or words that express the concept of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OrNull
    -0.09
    stras
    -0.08
    eer
    -0.08
    _aliases
    -0.07
    .alias
    -0.07
    baÅŁ
    -0.07
    ë©´ìłģ
    -0.07
     unut
    -0.07
    eec
    -0.07
    lopedia
    -0.07
    POSITIVE LOGITS
    tingham
    0.10
    ori
    0.10
     sure
    0.09
     least
    0.08
     surprisingly
    0.07
    ches
    0.07
     Sure
    0.07
    ched
    0.07
    urnal
    0.07
    ets
    0.07
    Act Density 0.066%

    No Known Activations