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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the importance of actions or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" or "A" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proceedings
    -0.70
    ":[
    -0.69
    antry
    -0.68
    Instruct
    -0.64
    imentary
    -0.63
    anism
    -0.63
     Orient
    -0.63
    hyde
    -0.63
     âĢİ
    -0.62
    aneously
    -0.61
    POSITIVE LOGITS
     lot
    1.23
    cknowled
    1.15
    HAHAHAHA
    1.01
     few
    1.01
     handful
    0.96
    usterity
    0.94
     curs
    0.93
    cknow
    0.93
    hem
    0.93
     glance
    0.91
    Act Density 0.299%

    No Known Activations