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

    Neuronpedia

    INDEX
    Explanations

    assertions about safety and carefulness in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.57
    ebenarnya
    -0.54
     uſed
    -0.53
     Roskov
    -0.52
    SpringBootTest
    -0.50
     noDo
    -0.50
     inherently
    -0.49
     ffilmiau
    -0.48
     reten
    -0.47
    كويكب
    -0.46
    POSITIVE LOGITS
     calmly
    1.68
     safely
    1.57
     confidently
    1.53
     quietly
    1.51
     happily
    1.50
     patiently
    1.45
     gracefully
    1.45
     smoothly
    1.45
     carefully
    1.42
     peacefully
    1.42
    Act Density 0.267%

    No Known Activations