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

    Neuronpedia

    INDEX
    Explanations

    technical terms, particularly those indicating equivalence or relationships in data and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esez
    -0.39
    日閲覧
    -0.38
    isSuccessful
    -0.36
    mę
    -0.35
    phemy
    -0.35
    清楚
    -0.35
    falla
    -0.35
     проду
    -0.35
    HostException
    -0.35
     متعلقه
    -0.34
    POSITIVE LOGITS
    ULT
    0.75
    tagHelperRunner
    0.75
     equivalent
    0.72
    equivalent
    0.67
     Equivalent
    0.67
     equivalents
    0.66
    Equivalent
    0.65
    Sul
    0.63
    ult
    0.61
     Sul
    0.61
    Act Density 1.719%

    No Known Activations