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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to" indicative of actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    κά
    -0.16
    cce
    -0.15
    /do
    -0.14
    zÃŃ
    -0.14
     Pax
    -0.14
    aida
    -0.14
    è®
    -0.14
    PUR
    -0.13
     пÑĢиÑħод
    -0.13
    èĶµ
    -0.13
    POSITIVE LOGITS
     become
    0.20
     create
    0.17
     warrant
    0.16
    D
    0.16
    yro
    0.15
    ilon
    0.15
     becomes
    0.15
    gether
    0.15
     form
    0.14
     produce
    0.14
    Act Density 0.060%

    No Known Activations