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

    Neuronpedia

    INDEX
    Explanations

    proper names and unique identifiers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities, particularly with a focus on names and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĭ
    -0.78
    CHAR
    -0.76
     Cla
    -0.76
     Chu
    -0.75
     sher
    -0.69
     CHAR
    -0.68
     chill
    -0.67
    Cla
    -0.67
     CSI
    -0.66
     Chung
    -0.66
    POSITIVE LOGITS
    Os
    1.15
    O
    1.10
     OD
    1.08
    Åį
    1.06
     Od
    1.05
    OC
    1.04
     Os
    1.03
    ost
    1.02
    OG
    1.01
     Olson
    1.00
    Act Density 0.545%

    No Known Activations