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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning a specific fact or projection

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases starting with "There are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ileaks
    -0.65
    otic
    -0.64
    speak
    -0.63
    icut
    -0.63
    rouse
    -0.62
     ordeal
    -0.62
     endeavour
    -0.62
     endeavor
    -0.61
    gypt
    -0.60
     Tower
    -0.60
    POSITIVE LOGITS
     plenty
    0.96
    女
    0.94
     exceptions
    0.91
    nces
    0.85
     indications
    0.84
     no
    0.81
     variations
    0.81
     similarities
    0.80
     occasions
    0.78
     lots
    0.78
    Act Density 0.080%

    No Known Activations