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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating admiration or seeking information about someone/something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "looked up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.63
    ching
    -0.61
    BAT
    -0.59
    redo
    -0.57
    Maker
    -0.56
    eers
    -0.56
    VA
    -0.56
    apo
    -0.56
    Ins
    -0.56
    oly
    -0.56
    POSITIVE LOGITS
    river
    0.90
    stairs
    0.74
    imate
    0.69
    WARD
    0.66
    wind
    0.66
    lights
    0.65
    horn
    0.64
    onyms
    0.62
    skirts
    0.61
    grades
    0.61
    Act Density 0.025%

    No Known Activations