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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing particular conditions or qualities that are notable or significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.15
    ém
    -0.14
    olik
    -0.14
    agar
    -0.14
    avit
    -0.14
    rex
    -0.14
    aret
    -0.14
    age
    -0.14
    Expression
    -0.13
    cribe
    -0.13
    POSITIVE LOGITS
     egregious
    0.15
    ĶåĽŀ
    0.15
     noteworthy
    0.15
    -interest
    0.15
     true
    0.15
    llum
    0.15
     fond
    0.14
     wenn
    0.14
    RIX
    0.14
    اتÙĩ
    0.14
    Act Density 0.031%

    No Known Activations