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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly in the context of praise or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argas
    -0.15
    fu
    -0.15
    ters
    -0.15
    aterno
    -0.14
    691
    -0.14
    ufe
    -0.14
    stuff
    -0.13
    ady
    -0.13
    ะ
    -0.13
    affer
    -0.13
    POSITIVE LOGITS
    istar
    0.15
    manent
    0.14
    azer
    0.14
    éĻµ
    0.14
    icode
    0.14
    urator
    0.14
    ución
    0.14
    BJECT
    0.14
    uns
    0.13
    oxic
    0.13
    Act Density 0.041%

    No Known Activations