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

    Neuronpedia

    INDEX
    Explanations

    terms indicating reliability or trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     logarith
    -0.45
    getFullYear
    -0.42
    StartTag
    -0.40
    ArrowToggle
    -0.39
    stalt
    -0.39
    ILON
    -0.39
     compartment
    -0.39
    nodoc
    -0.38
    StringBuffer
    -0.38
    sidemargin
    -0.38
    POSITIVE LOGITS
     trusted
    0.81
     reliable
    0.73
     Reliable
    0.71
    Reliable
    0.69
    reliable
    0.68
     confiable
    0.64
     Reliability
    0.63
    trusted
    0.62
     reliability
    0.61
     unreliable
    0.61
    Act Density 0.107%

    No Known Activations