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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Pro" or similar variations, indicating a focus on professional or proactive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    丸
    -0.16
    Leader
    -0.16
    ĭ
    -0.15
    pip
    -0.15
    ATTRIBUTE
    -0.15
    BUM
    -0.14
     Tribe
    -0.14
     Leader
    -0.14
    gende
    -0.13
    ardu
    -0.13
    POSITIVE LOGITS
    kud
    0.17
    dig
    0.16
     Pro
    0.16
    tti
    0.16
    -Pro
    0.15
    enza
    0.15
    ekl
    0.15
    instr
    0.15
    ivant
    0.15
    verbs
    0.15
    Act Density 0.017%

    No Known Activations