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

    Neuronpedia

    INDEX
    Explanations

    various characters that are not part of the English alphabet

    oai_token-act-pair · gpt-3.5-turbo

    specific character sequences or symbols commonly associated with names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    espie
    -0.75
    agascar
    -0.70
     marrow
    -0.70
     bearer
    -0.70
     resil
    -0.70
     rapt
    -0.69
    vantage
    -0.69
    ITNESS
    -0.68
     attendant
    -0.67
     tremend
    -0.67
    POSITIVE LOGITS
    Äį
    0.96
    ÃŃn
    0.86
    án
    0.83
    Å¡
    0.81
    ãĤ±
    0.80
    ti
    0.79
    ski
    0.78
    sky
    0.77
    kowski
    0.76
    ek
    0.76
    Act Density 0.012%

    No Known Activations