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

    Neuronpedia

    INDEX
    Explanations

    instances of characters speaking or expressing themselves in dialogue

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

    speaking and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    htaccess
    -0.40
     clavic
    -0.40
    INCIP
    -0.39
    Delimited
    -0.39
     glamour
    -0.39
     exper
    -0.38
     Lutz
    -0.38
     recurrent
    -0.38
     glycogen
    -0.38
     glam
    -0.38
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.66
    exitRule
    0.61
     propOrder
    0.56
    .*")]
    0.54
    RTHOOK
    0.54
    开口道
    0.50
    ubereitung
    0.49
    verwijspagina
    0.46
    Опис
    0.45
    CrossRef
    0.44
    Act Density 0.028%

    No Known Activations