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

    Neuronpedia

    INDEX
    Explanations

    references to companies, organizations, and trade sources

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters or entities denoted by single letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.70
     cort
    -0.65
    taboola
    -0.64
    aline
    -0.61
    ãĥĪ
    -0.61
     cir
    -0.60
     thous
    -0.60
    ãĥ¼
    -0.60
    ãĥ´
    -0.58
    paio
    -0.58
    POSITIVE LOGITS
    HS
    0.84
    HY
    0.83
    senal
    0.83
    ZI
    0.82
    ZA
    0.82
    KI
    0.81
    OPLE
    0.81
    KA
    0.79
    JD
    0.79
    INESS
    0.78
    Act Density 0.097%

    No Known Activations