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

    Neuronpedia

    INDEX
    Explanations

    instances of irony and ironic phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rum
    -0.16
    OLUMNS
    -0.15
    .googleapis
    -0.15
     Ban
    -0.15
    itel
    -0.15
     ACCEPT
    -0.14
    659
    -0.14
     SUBSTITUTE
    -0.13
    793
    -0.13
     rum
    -0.13
    POSITIVE LOGITS
    TEGER
    0.16
     tat
    0.16
     twists
    0.15
    Apis
    0.15
    ongo
    0.15
     Athen
    0.14
    cmc
    0.14
    å©
    0.14
    Radians
    0.14
    _REGISTRY
    0.14
    Act Density 0.008%

    No Known Activations