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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noop
    -0.14
     Alliance
    -0.14
     readability
    -0.14
     Heroes
    -0.14
     Ruf
    -0.13
    actor
    -0.13
    ÂĿ
    -0.13
    lander
    -0.13
    extent
    -0.13
     target
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.17
    elor
    0.16
    reas
    0.16
    deo
    0.16
    Fal
    0.15
    yg
    0.15
    nbsp
    0.15
    /or
    0.15
    rosse
    0.15
    redicate
    0.15
    Act Density 0.196%

    No Known Activations