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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating a commitment or assurance

    oai_token-act-pair · gpt-3.5-turbo

    references to promises and commitments made by individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.88
    ARS
    -0.76
    issue
    -0.75
    tis
    -0.73
    isol
    -0.72
    bin
    -0.71
    issues
    -0.71
    auto
    -0.71
    esthesia
    -0.70
    ento
    -0.70
    POSITIVE LOGITS
     promises
    0.96
     promised
    0.80
     promise
    0.79
     Gamble
    0.73
     Prom
    0.70
     pledges
    0.69
     assurances
    0.69
     promising
    0.68
     encour
    0.68
     anew
    0.67
    Act Density 0.012%

    No Known Activations