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

    Neuronpedia

    INDEX
    Explanations

    technical commands and programming structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aben
    -0.15
    .scalablytyped
    -0.15
     reprint
    -0.14
    ÎIJ
    -0.13
     tritur
    -0.13
    ĶåĽŀ
    -0.13
    ÑģÑĤÑĮ
    -0.12
    dera
    -0.12
    ublish
    -0.12
    imler
    -0.12
    POSITIVE LOGITS
     initial
    0.85
     init
    0.80
     Initial
    0.79
    initial
    0.79
    -initial
    0.75
    Initial
    0.74
     initialization
    0.72
     inicial
    0.72
    init
    0.71
    åĪĿå§ĭåĮĸ
    0.71
    Act Density 0.458%

    No Known Activations