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

    Neuronpedia

    INDEX
    Explanations

    punctuation or sentence-ending structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ves
    -0.15
    lew
    -0.14
     Pry
    -0.14
     Archives
    -0.14
    лад
    -0.14
    ertas
    -0.14
    iam
    -0.14
    illas
    -0.13
     Rena
    -0.13
     Unauthorized
    -0.13
    POSITIVE LOGITS
    /goto
    0.17
     Contents
    0.15
    uÃŃ
    0.15
     history
    0.15
     contents
    0.15
    History
    0.15
    olars
    0.14
    regnum
    0.14
    IDER
    0.14
    rett
    0.14
    Act Density 0.120%

    No Known Activations