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

    Neuronpedia

    INDEX
    Explanations

    names of specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific teams or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ."[
    -0.65
    "—
    -0.64
    )."
    -0.63
     undet
    -0.62
    ".[
    -0.61
    )—
    -0.61
    ").
    -0.59
    ãģĻ
    -0.59
    ).[
    -0.59
    ]."
    -0.58
    POSITIVE LOGITS
     meanwhile
    0.75
    ortium
    0.68
     welcomed
    0.56
    joined
    0.55
    eatures
    0.54
    ccording
    0.53
     echoed
    0.53
    ursday
    0.53
     launched
    0.52
     teamed
    0.52
    Act Density 1.598%

    No Known Activations