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

    Neuronpedia

    INDEX
    Explanations

    actions described in the form "As you can see"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perception or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oleon
    -0.75
    pan
    -0.72
    rang
    -0.70
    lam
    -0.69
    istries
    -0.67
    anmar
    -0.65
    ocaly
    -0.64
    addons
    -0.64
     Deng
    -0.63
    wcs
    -0.63
    POSITIVE LOGITS
    âĶĢ
    0.72
    ees
    0.71
     deduction
    0.70
    terday
    0.69
     (),
    0.69
     anecd
    0.63
    ,.
    0.61
    .—
    0.60
    UME
    0.60
    ,—
    0.60
    Act Density 0.071%

    No Known Activations