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

    Neuronpedia

    INDEX
    Explanations

    verbs related to commitments or assurances

    oai_token-act-pair · gpt-3.5-turbo

    statements of promises made by individuals, particularly in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.84
    andem
    -0.75
    wx
    -0.75
    Reviewer
    -0.71
    isol
    -0.70
    SO
    -0.69
    nesota
    -0.68
    etc
    -0.68
    opus
    -0.67
    mite
    -0.67
    POSITIVE LOGITS
     repeatedly
    0.69
    fulness
    0.68
     confidentiality
    0.68
     promises
    0.67
    llor
    0.67
     sacrific
    0.64
     Delivery
    0.62
     promised
    0.61
    ebus
    0.60
    grave
    0.60
    Act Density 0.034%

    No Known Activations