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

    Neuronpedia

    INDEX
    Explanations

    mentions of strong dedication or promises in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dedication or obligation to a cause or goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adish
    -0.77
     complexion
    -0.73
    ourning
    -0.69
    atin
    -0.67
    NetMessage
    -0.67
    phe
    -0.66
    oiler
    -0.66
    quer
    -0.65
    annis
    -0.65
     Moroc
    -0.65
    POSITIVE LOGITS
     commitment
    1.02
     allegiance
    0.93
     commitments
    0.91
     obligation
    0.78
    venant
    0.78
    gence
    0.76
    irmation
    0.76
    duty
    0.73
     pledges
    0.73
    ment
    0.72
    Act Density 0.023%

    No Known Activations