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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "pushing" or "push" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     charité
    -0.55
    الحياه
    -0.54
     âmes
    -0.54
     Redes
    -0.53
     STC
    -0.53
    ☺☺
    -0.52
     chauss
    -0.52
    epik
    -0.52
    conductors
    -0.52
     Barkley
    -0.51
    POSITIVE LOGITS
     push
    1.07
     pushes
    1.03
     pushed
    1.02
     Pushing
    1.01
     PUSH
    1.00
     pushing
    0.98
     Push
    0.94
    Pushing
    0.93
    push
    0.89
     buttons
    0.89
    Act Density 0.052%

    No Known Activations