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

    Neuronpedia

    INDEX
    Explanations

    terms related to validation or verification of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVAL
    -0.17
    iest
    -0.16
    lessly
    -0.15
    liness
    -0.15
    lical
    -0.14
    WER
    -0.14
    CRT
    -0.14
    undle
    -0.14
    lder
    -0.14
    ival
    -0.14
    POSITIVE LOGITS
    ated
    0.50
    ating
    0.42
    ations
    0.40
    ation
    0.38
    ator
    0.29
    ATED
    0.29
    ative
    0.28
    ators
    0.28
    ATION
    0.27
    ration
    0.26
    Act Density 0.083%

    No Known Activations