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

    Neuronpedia

    INDEX
    Explanations

    terms related to integration and collaborative efforts within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NING
    -0.17
     serialVersionUID
    -0.16
    dür
    -0.15
    ings
    -0.15
    매
    -0.14
    ratulations
    -0.14
    esda
    -0.14
    rung
    -0.14
    رÙĬر
    -0.14
    raki
    -0.14
    POSITIVE LOGITS
     into
    0.24
     Into
    0.20
    Into
    0.19
     seamlessly
    0.18
    iste
    0.18
    /embed
    0.18
    /ext
    0.18
    into
    0.17
     INTO
    0.16
     circuits
    0.16
    Act Density 0.025%

    No Known Activations