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

    Neuronpedia

    INDEX
    Explanations

    instances of "promise" related to commitments or assurances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kuuta
    -0.80
     استنادى
    -0.72
     Hayek
    -0.71
    fjspx
    -0.70
    évaluateur
    -0.68
    intios
    -0.67
    ILayout
    -0.66
     getField
    -0.64
    etcode
    -0.63
    uxxxx
    -0.63
    POSITIVE LOGITS
     promise
    1.76
     Promise
    1.75
    Promise
    1.64
     promises
    1.64
     Promises
    1.61
    promise
    1.55
     promised
    1.47
    Promises
    1.45
     promessa
    1.34
    promises
    1.31
    Act Density 0.083%

    No Known Activations