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

    Neuronpedia

    INDEX
    Explanations

    phrases related to equipment or tools

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eus
    -0.71
     Iranians
    -0.67
    ESE
    -0.66
    ONSORED
    -0.66
    Players
    -0.65
    selves
    -0.65
    izon
    -0.65
    swick
    -0.65
     Journals
    -0.65
    Goal
    -0.64
    POSITIVE LOGITS
     albeit
    1.14
     um
    0.83
    albeit
    0.82
     supra
    0.81
     huh
    0.80
     uh
    0.69
     though
    0.66
     unregulated
    0.66
     suburban
    0.64
     undisclosed
    0.64
    Act Density 0.192%

    No Known Activations