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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate countable items or measures

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

    numbers and numerical data presented in academic or technical contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.47
    Predecesor
    -0.44
     sebuah
    -0.41
    évaluateur
    -0.40
     larmes
    -0.40
     civilización
    -0.39
     zweier
    -0.39
    ContentAlignment
    -0.39
     dwóch
    -0.39
     setempat
    -0.38
    POSITIVE LOGITS
     forty
    0.94
     sixty
    0.93
     nine
    0.92
     sixteen
    0.91
     twenty
    0.91
     dozen
    0.91
     twelve
    0.90
     fourteen
    0.90
     eight
    0.90
     thirty
    0.89
    Act Density 0.683%

    No Known Activations