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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or notation related to scientific or mathematical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.58
    s
    -0.56
    ρίζ
    -0.56
     Cruz
    -0.55
     nervios
    -0.53
    witch
    -0.53
    ativas
    -0.52
    boxylic
    -0.52
     croce
    -0.51
    AGS
    -0.51
    POSITIVE LOGITS
    SI
    1.83
     SI
    1.78
    MI
    1.77
     PI
    1.76
     MI
    1.70
    DI
    1.64
    PI
    1.64
     FI
    1.58
     DI
    1.58
    BI
    1.56
    Act Density 0.101%

    No Known Activations