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

    Neuronpedia

    INDEX
    Explanations

    numerical strings and technical codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values mixed with code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     passionate
    -0.61
     sponsor
    -0.58
     roadside
    -0.57
     announcement
    -0.57
     demand
    -0.57
     caution
    -0.57
     trimmed
    -0.56
     safeguards
    -0.56
     mathemat
    -0.56
     gam
    -0.56
    POSITIVE LOGITS
    uchi
    0.88
    sac
    0.86
    tx
    0.81
    pta
    0.81
    rage
    0.80
    oops
    0.80
    fu
    0.79
    uminium
    0.78
    eri
    0.78
    shapeshifter
    0.77
    Act Density 0.216%

    No Known Activations