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

    Neuronpedia

    INDEX
    Explanations

    lists or items in articles

    oai_token-act-pair · gpt-3.5-turbo

    lists or rankings of items or tips

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isphere
    -0.65
    bered
    -0.63
    brance
    -0.63
    ersion
    -0.62
     subdivision
    -0.61
    ivism
    -0.61
    assembly
    -0.61
    managed
    -0.61
    aline
    -0.60
    division
    -0.59
    POSITIVE LOGITS
     Reasons
    1.49
     Things
    1.28
     Ways
    1.27
     reasons
    1.09
     Signs
    1.07
     coolest
    1.07
     Worst
    1.03
     Questions
    1.03
     ways
    1.02
     things
    0.99
    Act Density 0.096%

    No Known Activations