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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating mathematical relationships involving factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogen
    -1.53
    okinetic
    -1.50
    ometric
    -1.40
    aments
    -1.40
    ocracy
    -1.40
    ibil
    -1.38
     negatively
    -1.37
     increasingly
    -1.34
    ational
    -1.33
     hurt
    -1.31
    POSITIVE LOGITS
    ĨĴ
    2.19
    <|outofrange|>
    2.02
     ↵
    2.02
           ↵
    2.02
    ↵
    2.02
    <|outofrange|>
    2.02
    ↵↵
    2.02
    <|outofrange|>
    2.02
    2.02
    ↵  ³³³
    2.02
    Act Density 0.058%

    No Known Activations