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

    Neuronpedia

    INDEX
    Explanations

    references to the action of pushing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    moveToFirst
    -0.54
    UAWEI
    -0.45
    colnshire
    -0.43
     հղումներ
    -0.42
    Rhestr
    -0.40
     OnTrigger
    -0.38
    めでとう
    -0.38
    comuna
    -0.37
    :✨
    -0.37
    CloseOperation
    -0.37
    POSITIVE LOGITS
     PUSH
    0.79
    Push
    0.78
     Push
    0.77
     push
    0.75
     pusher
    0.72
     pushing
    0.71
    push
    0.70
     pushes
    0.68
    PUSH
    0.67
     Pushing
    0.61
    Act Density 1.687%

    No Known Activations