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

    Neuronpedia

    INDEX
    Explanations

    phrases and statements related to personal reflections or decisions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of common phrases and rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.63
    olson
    -0.63
    javascript
    -0.61
    earch
    -0.60
    SPONSORED
    -0.60
    iceps
    -0.60
    ridor
    -0.60
    ],"
    -0.59
    ê
    -0.59
     ÂŃ
    -0.58
    POSITIVE LOGITS
    cknowled
    0.79
    oret
    0.78
    cknow
    0.73
    eday
    0.73
    entimes
    0.66
    neath
    0.64
     importantly
    0.63
     Stupid
    0.61
     blat
    0.61
     consequence
    0.59
    Act Density 0.799%

    No Known Activations