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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly percentages and decimals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.51
     längre
    -0.51
     connexes
    -0.49
     longest
    -0.49
     længere
    -0.48
    adeira
    -0.47
    블
    -0.45
     Horst
    -0.44
     μά
    -0.44
     Kaplan
    -0.44
    POSITIVE LOGITS
    RegistryLite
    0.84
    GEBURTSDATUM
    0.80
    SharedDtor
    0.77
    Datuak
    0.77
    <bos>
    0.75
    DebuggerStep
    0.72
     <",
    0.72
    Diwedd
    0.72
    jooq
    0.71
    tagHelperRunner
    0.71
    Act Density 0.572%

    No Known Activations