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

    Neuronpedia

    INDEX
    Explanations

    references to habitual behaviors and traditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mandate
    -0.17
    ollen
    -0.15
    ion
    -0.15
     Conc
    -0.14
    ameron
    -0.14
     Universal
    -0.14
    emplates
    -0.14
    achment
    -0.14
    ER
    -0.14
    er
    -0.14
    POSITIVE LOGITS
    TEGER
    0.19
     habits
    0.17
    .CopyTo
    0.16
    ousand
    0.15
    umber
    0.15
     habit
    0.15
    lrt
    0.14
     Setter
    0.14
    ä¹ł
    0.14
    bih
    0.14
    Act Density 0.044%

    No Known Activations