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

    Neuronpedia

    INDEX
    Explanations

    arguments related to responsibility and accountability in social and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "to," "had," or "would."

    np_acts-logits-general · gemini-2.0-flash

    properly or correctly done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    -0.68
    detectChanges
    -0.58
    بوابة
    -0.57
    żli
    -0.56
    ResumeLayout
    -0.56
    BeginInit
    -0.56
    ViewData
    -0.55
    andExpect
    -0.53
     mxArray
    -0.52
     незавершена
    -0.52
    POSITIVE LOGITS
     properly
    0.87
     PROPER
    0.82
     proper
    0.80
    Proper
    0.76
     respect
    0.75
     Properly
    0.73
     correctement
    0.71
     Respect
    0.70
     corect
    0.69
     correctly
    0.68
    Act Density 0.348%

    No Known Activations