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

    Neuronpedia

    INDEX
    Explanations

    sentences that evaluate credibility and reliability of information related to belief systems or personal judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CharCode
    -0.15
    exion
    -0.14
     strncmp
    -0.14
     discharged
    -0.14
    ropp
    -0.14
    indsight
    -0.14
    jin
    -0.14
    ugar
    -0.14
    BindingUtil
    -0.14
    ë¹Ļ
    -0.13
    POSITIVE LOGITS
     likely
    0.18
    addtogroup
    0.18
    pot
    0.17
    likely
    0.17
     Likely
    0.17
    åĿ
    0.16
     bulk
    0.15
     Bulk
    0.15
     potential
    0.15
    matic
    0.15
    Act Density 0.166%

    No Known Activations