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

    Neuronpedia

    INDEX
    Explanations

    references to the sky

    oai_token-act-pair · gpt-3.5-turbo

    references to the sky

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.83
    utic
    -0.78
    regor
    -0.77
    ective
    -0.76
     Polit
    -0.75
    ivities
    -0.71
    udes
    -0.71
    ublic
    -0.71
    utics
    -0.70
    atives
    -0.70
    POSITIVE LOGITS
    hawk
    1.01
     skies
    0.97
    scape
    0.95
     sky
    0.93
    watching
    0.92
    fall
    0.92
    plane
    0.90
    walk
    0.89
    rock
    0.89
    burst
    0.88
    Act Density 0.020%

    No Known Activations