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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and casual expressions that indicate reassurance or uncertainty

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

    but; however; normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disponibilités
    -0.46
     HttpNotFound
    -0.41
    StoryboardSegue
    -0.40
    localctx
    -0.39
    colorbar
    -0.39
    Highly
    -0.37
     Highly
    -0.36
     successo
    -0.36
     nakalista
    -0.36
    Composable
    -0.36
    POSITIVE LOGITS
     okay
    0.65
     OK
    0.59
    okay
    0.56
     Normal
    0.54
    Normal
    0.54
     норма
    0.54
    許
    0.53
     Acceptable
    0.52
     tolerable
    0.52
     Norm
    0.51
    Act Density 0.047%

    No Known Activations