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

    Neuronpedia

    INDEX
    Explanations

    hyphenated compound words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term considerations or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GEAR
    -0.86
     Scrib
    -0.86
     DRAG
    -0.77
     Cosponsors
    -0.77
     AVG
    -0.76
    ħĭ
    -0.76
     Phi
    -0.74
     Compass
    -0.74
    ãĤ¡
    -0.73
     Yelp
    -0.72
    POSITIVE LOGITS
    serving
    1.07
    term
    1.06
    sized
    1.04
    eyed
    1.02
    distance
    1.02
    enough
    1.01
    generation
    0.96
    legged
    0.96
    circ
    0.95
    range
    0.95
    Act Density 0.060%

    No Known Activations