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

    Neuronpedia

    INDEX
    Explanations

    keywords related to recognition or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "recognize" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stead
    -0.75
    ffield
    -0.74
    isoft
    -0.71
    quin
    -0.68
    ixt
    -0.68
    acho
    -0.66
    ocalypse
    -0.66
    hire
    -0.65
    isher
    -0.65
     sandwich
    -0.63
    POSITIVE LOGITS
    ibly
    1.00
    ledged
    0.90
    enance
    0.87
    ibility
    0.85
    recogn
    0.83
    ably
    0.83
     recognize
    0.81
    rities
    0.78
     recognizing
    0.78
    ected
    0.74
    Act Density 0.022%

    No Known Activations