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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to various topics and categories, including food, profession, and community concepts

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

    [token] following specific token

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.63
    ſchaft
    -0.61
    delli
    -0.57
    tanleria
    -0.57
    ſammen
    -0.57
    iſchen
    -0.56
    ſelben
    -0.55
    DECREF
    -0.55
    iſen
    -0.54
    iſten
    -0.54
    POSITIVE LOGITS
    قایناقلار
    0.45
     officiers
    0.36
    devamını
    0.35
     démocr
    0.35
     boken
    0.34
     féd
    0.32
     hotell
    0.32
     revanche
    0.31
     métiers
    0.31
    casila
    0.30
    Act Density 0.509%

    No Known Activations