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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wel" and its variations, indicating a focus on positive greetings or welcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hana
    -0.17
    eced
    -0.15
    abil
    -0.15
    993
    -0.14
    viders
    -0.14
    Tail
    -0.14
     Anast
    -0.14
    elli
    -0.14
    elenium
    -0.14
    neau
    -0.14
    POSITIVE LOGITS
    ittle
    0.19
    ryn
    0.18
    ington
    0.17
    .SizeMode
    0.16
    _defined
    0.15
    ì²´
    0.15
    chsel
    0.15
    anko
    0.14
    INGTON
    0.14
    -Identifier
    0.14
    Act Density 0.019%

    No Known Activations