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

    Neuronpedia

    INDEX
    Explanations

    em-dashes and various forms of long dashes or hyphens

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

    Text before and after double dashes

    np_acts-logits-general · gemini-2.0-flash

    --Fe conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagLayout
    -0.77
    ponses
    -0.69
    ROIT
    -0.67
    Nuorodos
    -0.65
     esternos
    -0.65
    bootstrapcdn
    -0.65
    SharedDtor
    -0.65
    endfor
    -0.64
     Leal
    -0.63
    PreferredItem
    -0.63
    POSITIVE LOGITS
    ————————————————
    0.90
    ———
    0.89
    —————
    0.75
    ––
    0.74
    ————————
    0.73
    ————
    0.72
     Wikipédia
    0.72
    ——
    0.71
    //--
    0.70
    >−
    0.70
    Act Density 0.294%

    No Known Activations