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

    Neuronpedia

    INDEX
    Explanations

    references to commitments or promises

    oai_token-act-pair · gpt-3.5-turbo

    references to commitments or promises made, particularly in the context of pledges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.82
    occ
    -0.68
    rup
    -0.67
    ROR
    -0.67
    ĻĤ
    -0.63
    sle
    -0.62
    iris
    -0.62
    apple
    -0.61
     Riding
    -0.61
     Bing
    -0.60
    POSITIVE LOGITS
     pledge
    1.41
     pledges
    1.37
     Pledge
    1.17
     pledging
    1.12
     pled
    0.94
     commitments
    0.89
    ylum
    0.88
     allegiance
    0.87
     encour
    0.82
    heit
    0.81
    Act Density 0.008%

    No Known Activations