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

    Neuronpedia

    INDEX
    Explanations

    terms related to substitutions or replacements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vidare
    -0.62
    اریخ
    -0.57
     videre
    -0.56
     gjen
    -0.56
     spéciales
    -0.56
     entour
    -0.53
     forbindelse
    -0.53
    StructEnd
    -0.53
     riguardo
    -0.51
     hvid
    -0.50
    POSITIVE LOGITS
    UserScript
    0.85
    principalColumn
    0.78
    ioutil
    0.71
     Replace
    0.69
    IntentFilter
    0.66
     replaces
    0.66
     REPLACE
    0.66
    usehen
    0.64
    isole
    0.64
    sipasi
    0.63
    Act Density 0.132%

    No Known Activations