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

    Neuronpedia

    INDEX
    Explanations

    phrases related to singularity or individuality

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "single" or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akings
    -0.89
    Downloadha
    -0.84
    apons
    -0.78
    acists
    -0.74
    ooks
    -0.73
    raints
    -0.72
    enaries
    -0.72
    orsi
    -0.70
    acements
    -0.70
    ravings
    -0.68
    POSITIVE LOGITS
    handedly
    1.16
     digit
    1.01
    player
    0.92
    ton
    0.90
     minute
    0.89
     digits
    0.88
     sided
    0.86
     piece
    0.85
     molecule
    0.83
     person
    0.80
    Act Density 0.021%

    No Known Activations