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

    Neuronpedia

    INDEX
    Explanations

    proper names and unique terms, especially those with spaces between them

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the letter 'a'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    t
    -0.78
    l
    -0.68
    bart
    -0.68
    tons
    -0.68
    y
    -0.68
    ties
    -0.67
    c
    -0.66
    nw
    -0.66
    mie
    -0.65
    n
    -0.65
    POSITIVE LOGITS
    usterity
    1.11
    ñ
    1.06
    ç
    1.06
    issance
    1.04
    veland
    1.02
    ña
    0.99
    esthesia
    0.97
    esthetic
    0.95
    ÅŁ
    0.92
    emia
    0.91
    Act Density 0.110%

    No Known Activations