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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating human interaction and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪÛĮØ´
    -0.17
    ida
    -0.15
    336
    -0.14
    asca
    -0.14
    sons
    -0.14
     rs
    -0.14
     Lives
    -0.13
     Merrill
    -0.13
    responseData
    -0.13
     crossorigin
    -0.13
    POSITIVE LOGITS
    hack
    0.14
    eki
    0.14
    _yield
    0.14
    ype
    0.14
    acias
    0.13
    ulk
    0.13
     Lorem
    0.13
    sko
    0.13
     lawy
    0.13
    anz
    0.13
    Act Density 0.279%

    No Known Activations