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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.79
    enterOuterAlt
    -0.75
     critique
    -0.67
    PostInfinity
    -0.65
     criti
    -0.63
    uali
    -0.63
    iomanip
    -0.60
    disambiguation
    -0.60
    rungsseite
    -0.58
     крити
    -0.58
    POSITIVE LOGITS
     jotka
    0.48
     lograron
    0.46
    extendable
    0.46
     rilass
    0.45
    리를
    0.45
    esez
    0.45
    ấc
    0.44
     neler
    0.43
     furnishes
    0.43
    estors
    0.43
    Act Density 0.093%

    No Known Activations