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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-identification or self-describing entities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     XIII
    -0.76
    IUM
    -0.74
     Ashe
    -0.71
     Rouge
    -0.71
    rium
    -0.68
     Syndicate
    -0.67
    ICAN
    -0.67
    mingham
    -0.66
     Nights
    -0.66
    ī
    -0.65
    POSITIVE LOGITS
    destruct
    1.23
    lessly
    1.09
     destruct
    1.06
    same
    1.06
     explanatory
    1.00
    ridges
    0.98
    contained
    0.95
    conscious
    0.90
    proclaimed
    0.89
    pecially
    0.87
    Act Density 0.022%

    No Known Activations