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

    Neuronpedia

    INDEX
    Explanations

    words related to declarations or claims

    oai_token-act-pair · gpt-3.5-turbo

    references to declaration or classification terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIP
    -0.71
     è£ı
    -0.69
     tremend
    -0.67
    awaru
    -0.65
    ãĤ®
    -0.64
    ãĥ´ãĤ¡
    -0.64
    BALL
    -0.63
    κ
    -0.62
    DEM
    -0.61
    Bey
    -0.61
    POSITIVE LOGITS
    osures
    1.09
    avier
    1.04
    othes
    1.04
    osing
    0.98
    iff
    0.98
    ipper
    0.97
    inic
    0.96
    arent
    0.95
    utch
    0.95
    uster
    0.94
    Act Density 0.012%

    No Known Activations