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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surpassing limits or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRO
    -0.17
    rack
    -0.17
    iros
    -0.15
    isch
    -0.15
     Aeros
    -0.14
    drop
    -0.14
    cone
    -0.14
    à¤Ĺल
    -0.14
     Nut
    -0.14
    ÏĢο
    -0.14
    POSITIVE LOGITS
    ambre
    0.14
    ioni
    0.14
     ap
    0.14
    иÑģÑĤÑĢа
    0.14
    876
    0.14
     Guth
    0.14
    -ln
    0.14
    991
    0.13
    ettle
    0.13
    994
    0.13
    Act Density 0.032%

    No Known Activations