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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote transitional or conditional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyse
    -0.16
    erca
    -0.15
    ascar
    -0.15
    -circle
    -0.15
    mour
    -0.15
    anners
    -0.15
    onical
    -0.14
    avian
    -0.14
    rollable
    -0.14
    one
    -0.14
    POSITIVE LOGITS
    /am
    0.24
     two
    0.20
    between
    0.18
    409
    0.17
    isode
    0.17
     sexes
    0.17
     innings
    0.17
    umi
    0.16
    DEX
    0.16
     between
    0.16
    Act Density 0.046%

    No Known Activations