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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "The" at the beginning of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.77
    #$
    -0.72
    .</
    -0.72
    Ïī
    -0.70
    models
    -0.70
    Layer
    -0.70
    !.
    -0.70
    GPU
    -0.69
    ÏĢ
    -0.69
    ����
    -0.69
    POSITIVE LOGITS
    resa
    1.52
    odore
    1.41
     announcement
    1.16
     Associated
    1.11
     revelation
    1.10
     latest
    1.04
     move
    0.97
    oret
    0.95
     revelations
    0.94
     irony
    0.92
    Act Density 0.270%

    No Known Activations