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

    Neuronpedia

    INDEX
    Explanations

    internet URLs

    oai_token-act-pair · gpt-3.5-turbo

    links or references to URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frie
    -0.69
    oux
    -0.68
     Camden
    -0.64
     deficiencies
    -0.61
    lot
    -0.61
     Scores
    -0.60
     Vie
    -0.60
     renovation
    -0.60
     Lak
    -0.59
     Norwich
    -0.59
    POSITIVE LOGITS
    verage
    0.83
    xon
    0.80
    hm
    0.77
    daq
    0.77
    ffee
    0.76
    cko
    0.74
    Eng
    0.74
    gov
    0.73
    opher
    0.73
    jon
    0.72
    Act Density 0.009%

    No Known Activations