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

    Neuronpedia

    INDEX
    Explanations

    references to divine commands and societal regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dad
    -0.15
    MenuStrip
    -0.15
    inger
    -0.15
    Attempt
    -0.14
    vez
    -0.14
    velope
    -0.14
    ussen
    -0.14
    天åłĤ
    -0.14
     recep
    -0.14
     multiples
    -0.14
    POSITIVE LOGITS
     [=
    0.20
     meanwhile
    0.19
     [
    0.19
     thus
    0.16
     [*
    0.16
     shall
    0.16
    (cf
    0.16
     escort
    0.16
     Israel
    0.16
     Scaling
    0.15
    Act Density 0.022%

    No Known Activations