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

    Neuronpedia

    INDEX
    Explanations

    references to credibility, including words related to trustworthiness and reliability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to credibility and trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meal
    -0.75
     Boat
    -0.72
     Nurs
    -0.71
     Parenthood
    -0.69
    hap
    -0.68
     Klu
    -0.65
    Ò
    -0.63
     Abandon
    -0.63
    Pause
    -0.63
    akings
    -0.63
    POSITIVE LOGITS
    ibly
    1.25
    ulously
    1.20
    enza
    1.20
     cred
    1.11
    ulous
    1.11
    iosity
    0.92
    ibles
    0.91
    ibility
    0.89
    entials
    0.88
    icator
    0.87
    Act Density 0.009%

    No Known Activations