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

    Neuronpedia

    INDEX
    Explanations

    references to specific code annotations or documentation structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neve
    -0.69
    StructEnd
    -0.67
    =’
    -0.63
    moveToFirst
    -0.63
     Meksiku
    -0.62
    ’,
    -0.59
    ival
    -0.58
     lant
    -0.58
     Calib
    -0.58
     Silicon
    -0.58
    POSITIVE LOGITS
     {@
    2.59
    {@
    2.15
    >{@
    1.53
     '{@
    1.35
    }{@
    1.21
     ${\
    0.95
     @{
    0.93
     }{@
    0.92
    ${\
    0.88
    _{{\
    0.88
    Act Density 0.081%

    No Known Activations