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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases related to recognition or success

    oai_token-act-pair · gpt-3.5-turbo

    terms related to awards and their connotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Semitism
    -0.71
     Taxes
    -0.70
     Solitaire
    -0.68
     Libraries
    -0.66
     syndrome
    -0.65
     Tags
    -0.64
    clerosis
    -0.64
     Jackets
    -0.62
     charms
    -0.61
     Grants
    -0.60
    POSITIVE LOGITS
    acious
    1.11
    urable
    1.09
    uous
    1.06
    liest
    1.05
    ishable
    1.04
    ously
    1.01
    uable
    0.99
    proven
    0.99
    less
    0.98
    iously
    0.97
    Act Density 0.506%

    No Known Activations