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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "match" or related concepts indicating alignment or compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ury
    -0.18
    ekil
    -0.17
    xon
    -0.15
     pimp
    -0.15
     jsonResponse
    -0.15
    hek
    -0.14
    hte
    -0.14
    aho
    -0.14
    uen
    -0.14
    Å¡k
    -0.14
    POSITIVE LOGITS
    ingly
    0.25
    DispatchToProps
    0.16
    ãĥ§
    0.15
    DMIN
    0.15
    older
    0.15
    ting
    0.15
    ron
    0.15
    able
    0.15
    imer
    0.15
    ably
    0.15
    Act Density 0.051%

    No Known Activations