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

    Neuronpedia

    INDEX
    Explanations

    verbs and actions that imply movement or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.61
     AssemblyCompany
    -0.52
    Personensuche
    -0.49
    while
    -0.49
    Portale
    -0.48
     beginnetje
    -0.48
     Meksiku
    -0.48
    تقاوى
    -0.47
     whilst
    -0.46
    Panamoan
    -0.46
    POSITIVE LOGITS
     squarely
    0.94
     neatly
    0.79
     firmly
    0.75
     comfortably
    0.71
     seamlessly
    0.70
     heavily
    0.67
     solidly
    0.66
     unmistak
    0.65
     nicely
    0.64
     powerfully
    0.63
    Act Density 0.480%

    No Known Activations