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

    Neuronpedia

    INDEX
    Explanations

    phrases related to outer space and space exploration

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "space" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UCT
    -0.73
     Snyder
    -0.71
    inger
    -0.68
     Rove
    -0.67
     presumptive
    -0.65
    JUST
    -0.64
    CLOSE
    -0.64
    usted
    -0.63
    enance
    -0.63
    ombie
    -0.63
    POSITIVE LOGITS
    flight
    1.29
    plane
    0.97
     shuttle
    0.93
    planes
    0.89
     exploration
    0.89
    gravity
    0.87
    uits
    0.87
     habitats
    0.86
    kat
    0.85
    ategory
    0.83
    Act Density 0.026%

    No Known Activations