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

    Neuronpedia

    INDEX
    Explanations

    words posing questions or raising issues

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or questions about "the" and its associated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icism
    -0.85
    cation
    -0.81
    matter
    -0.81
    leness
    -0.81
    iliation
    -0.80
    rama
    -0.80
    cture
    -0.79
    obook
    -0.79
    analysis
    -0.78
    hyde
    -0.77
    POSITIVE LOGITS
     indications
    1.16
     exceptions
    1.07
     signs
    1.06
     words
    1.04
     constants
    1.04
     truths
    1.00
     kinds
    0.99
     moments
    0.99
     nods
    0.98
     keys
    0.98
    Act Density 0.176%

    No Known Activations