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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical or abstract spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to "space" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brach
    -0.73
    tip
    -0.71
    amaz
    -0.69
    bane
    -0.67
    anism
    -0.65
     adul
    -0.62
    aic
    -0.62
     Browne
    -0.61
    ahon
    -0.61
    fam
    -0.60
    POSITIVE LOGITS
     space
    3.86
     spaces
    2.77
    space
    2.76
     Space
    2.60
     SPACE
    2.39
    Space
    2.25
     Spaces
    2.08
     spac
    1.91
    pace
    1.60
     orbit
    1.39
    Act Density 0.023%

    No Known Activations