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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating composition or construction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ira
    -0.74
    AIDS
    -0.74
    uer
    -0.72
    lly
    -0.72
    aura
    -0.70
    mb
    -0.70
    Sport
    -0.70
    Answer
    -0.70
    hr
    -0.68
    abba
    -0.67
    POSITIVE LOGITS
     several
    0.99
     disparate
    0.98
     varying
    0.97
     multiple
    0.97
     three
    0.95
     four
    0.95
     various
    0.93
     five
    0.93
     seven
    0.90
     two
    0.90
    Act Density 0.108%

    No Known Activations