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

    Neuronpedia

    INDEX
    Explanations

    words related to reliability and trustworthiness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reliability and trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovember
    -0.91
    ylum
    -0.75
    ophon
    -0.75
    aeper
    -0.75
    ĸļ
    -0.73
    abeth
    -0.73
    ophy
    -0.72
    hoff
    -0.71
    borough
    -0.70
    eanor
    -0.70
    POSITIVE LOGITS
     reliable
    1.15
     narrator
    1.04
     trustworthy
    0.99
     source
    0.96
     sources
    0.95
     predictor
    0.89
     indicator
    0.88
     unreliable
    0.88
     indicators
    0.85
    mate
    0.82
    Act Density 0.064%

    No Known Activations