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

    Neuronpedia

    INDEX
    Explanations

    instances of events or items making their first appearance or being introduced

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "debut" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fax
    -0.68
    enough
    -0.68
    Downloadha
    -0.65
    GO
    -0.64
    hate
    -0.63
    learn
    -0.63
    gor
    -0.60
     Boh
    -0.58
    average
    -0.57
     Rutherford
    -0.57
    POSITIVE LOGITS
    antes
    1.43
    ante
    1.30
    ants
    1.09
    ant
    1.03
    antly
    0.95
    ary
    0.85
     episode
    0.82
     album
    0.78
    ees
    0.77
    ing
    0.76
    Act Density 0.057%

    No Known Activations