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

    Neuronpedia

    INDEX
    Explanations

    words related to objects or concepts that are available or accessible for some form of use or interaction

    oai_token-act-pair · gpt-3.5-turbo

    words related to items that are capable of being modified, transformed, or made accessible

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auri
    -0.90
    ËĪ
    -0.86
    erva
    -0.85
    ster
    -0.75
    itia
    -0.74
    alyst
    -0.74
    sters
    -0.73
    iversary
    -0.73
    sterdam
    -0.72
    otor
    -0.71
    POSITIVE LOGITS
    ible
    0.79
    ibility
    0.75
    ledged
    0.70
    itably
    0.70
     Mae
    0.68
    IBLE
    0.66
    ibly
    0.66
    vous
    0.64
     cords
    0.63
    ibles
    0.61
    Act Density 0.027%

    No Known Activations