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

    Neuronpedia

    INDEX
    Explanations

    actions associated with pushing or making progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whiteColor
    -0.70
    mycompany
    -0.70
    listdir
    -0.63
     portátil
    -0.63
     Ston
    -0.61
    cein
    -0.61
    amentul
    -0.59
     oreilles
    -0.59
    toner
    -0.58
     Coates
    -0.58
    POSITIVE LOGITS
     push
    1.89
     PUSH
    1.69
     pushes
    1.68
     Pushing
    1.67
     Push
    1.66
     pushed
    1.60
     pushing
    1.60
     pusher
    1.58
    push
    1.57
    Pushing
    1.54
    Act Density 0.074%

    No Known Activations