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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and official documents or statements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "cl", potentially indicating a focus on classifications or categorizations related to clarity or enclosure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gers
    -0.74
    κ
    -0.73
    sel
    -0.63
    BIP
    -0.61
    BALL
    -0.61
     Democr
    -0.60
     tremend
    -0.59
     rabbits
    -0.59
     dilig
    -0.59
    awaru
    -0.59
    POSITIVE LOGITS
    osing
    1.17
    osures
    1.13
    oser
    1.05
    inic
    1.02
    othes
    1.01
    uster
    1.01
    avier
    1.00
    oak
    0.97
    aration
    0.97
    arent
    0.95
    Act Density 0.024%

    No Known Activations