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

    Neuronpedia

    INDEX
    Explanations

    quotations within texts

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol that appears frequently in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CLR
    -0.65
     paperback
    -0.64
     Wilmington
    -0.64
     Sussex
    -0.63
    undown
    -0.63
     Palestin
    -0.61
     satell
    -0.58
     Byz
    -0.58
     carbohyd
    -0.57
     Juda
    -0.56
    POSITIVE LOGITS
    ï¸ı
    1.04
    agree
    0.82
    DEN
    0.78
    mand
    0.77
    kay
    0.76
    felt
    0.74
    tal
    0.74
    tarian
    0.72
    tu
    0.72
    entity
    0.72
    Act Density 0.154%

    No Known Activations