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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks that indicate speech or pauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     particularly
    -0.19
    ARIANT
    -0.15
     especially
    -0.14
     therefore
    -0.14
    irmed
    -0.14
    Therefore
    -0.14
     Angebot
    -0.14
     Provide
    -0.14
    particularly
    -0.14
     Therefore
    -0.13
    POSITIVE LOGITS
     nearby
    0.26
     Seconds
    0.26
     Minutes
    0.22
     Moments
    0.22
     Behind
    0.22
     Suddenly
    0.22
     Nearby
    0.21
    Minutes
    0.20
     Across
    0.20
     Flames
    0.20
    Act Density 0.238%

    No Known Activations