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

    Neuronpedia

    INDEX
    Explanations

    abbreviations with the format "E." followed by a single letter

    oai_token-act-pair · gpt-3.5-turbo

    punctuated sentences indicating significant moments or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latitude
    -0.76
    wcs
    -0.74
    eele
    -0.71
     fixme
    -0.66
    hari
    -0.65
    ioned
    -0.65
     neutrality
    -0.63
    alysed
    -0.62
     comprom
    -0.62
    arios
    -0.62
    POSITIVE LOGITS
     coli
    1.39
    TERN
    0.90
     Cummings
    0.84
    mail
    0.82
     Coy
    0.76
    mails
    0.75
     Howard
    0.73
    Sah
    0.70
    sports
    0.68
    theless
    0.68
    Act Density 0.021%

    No Known Activations