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

    Neuronpedia

    INDEX
    Explanations

    instances of notable examples or cases in various discussions, particularly in relation to criticism or issues

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

    "examples" or its variants

    np_acts-logits-general · gemini-2.0-flash

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.55
     propOrder
    -0.47
    ientras
    -0.47
     endfor
    -0.44
     '\\;'
    -0.44
     beginnetje
    -0.43
     igenom
    -0.41
    tagHelperRunner
    -0.41
    vänt
    -0.40
     arbete
    -0.40
    POSITIVE LOGITS
     examples
    0.56
     recent
    0.51
     Beispiele
    0.47
     recenti
    0.46
     recently
    0.43
     instances
    0.43
     AttributeSet
    0.42
     esempi
    0.42
     EXAMPLES
    0.42
    recently
    0.41
    Act Density 0.683%

    No Known Activations