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

    Neuronpedia

    INDEX
    Explanations

    technical terms and metrics related to data analysis and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regress
    -0.15
    rans
    -0.15
     starter
    -0.14
    apult
    -0.14
    edException
    -0.14
     Coff
    -0.13
    roman
    -0.13
     Ðļод
    -0.13
    ª
    -0.13
    abis
    -0.13
    POSITIVE LOGITS
     false
    0.39
    false
    0.36
     precision
    0.33
     accuracy
    0.32
     False
    0.31
     Receiver
    0.31
    False
    0.31
     Precision
    0.29
     receiver
    0.28
    /false
    0.28
    Act Density 0.041%

    No Known Activations