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

    Neuronpedia

    INDEX
    Explanations

    references to steps in a process, particularly those denoted as "Step" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.74
     Exacts
    -0.63
    carpus
    -0.63
     Pringle
    -0.63
    </tfoot>
    -0.59
     Италијани
    -0.59
    tonsoft
    -0.59
    AccessorTable
    -0.58
     nakalista
    -0.58
    LIBRA
    -0.58
    POSITIVE LOGITS
     inégal
    0.66
    Externí
    0.65
    Step
    0.60
     PLWABN
    0.58
     vérité
    0.57
    TRUE
    0.57
     costumi
    0.57
     éprou
    0.56
    Datuak
    0.56
     anche
    0.55
    Act Density 0.058%

    No Known Activations