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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "welcome" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĢ
    -0.15
    ikal
    -0.15
    iler
    -0.15
    orc
    -0.15
    imus
    -0.15
    ocity
    -0.14
    ervo
    -0.14
    orio
    -0.13
    .RightToLeft
    -0.13
    reon
    -0.13
    POSITIVE LOGITS
     part
    0.15
    izzard
    0.14
    æĮģç»Ń
    0.14
    icone
    0.14
    /Peak
    0.14
    hoa
    0.14
    aison
    0.13
    ngör
    0.13
    nger
    0.13
    thood
    0.13
    Act Density 0.013%

    No Known Activations