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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the effectiveness or appropriateness of choices and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indsight
    -0.17
     various
    -0.16
     better
    -0.15
    YRO
    -0.14
    arine
    -0.14
     more
    -0.13
    IEW
    -0.13
    anches
    -0.13
    cope
    -0.13
     Affairs
    -0.13
    POSITIVE LOGITS
     combination
    0.32
     kind
    0.30
     amount
    0.30
     kinds
    0.25
    combination
    0.25
     mix
    0.25
     balance
    0.25
     thing
    0.25
    amount
    0.24
    /right
    0.24
    Act Density 0.053%

    No Known Activations