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

    Neuronpedia

    INDEX
    Explanations

    terms related to organization and classification in alphabetical order

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kramer
    -0.17
    ability
    -0.16
    pta
    -0.15
    union
    -0.14
    ASTE
    -0.14
     Forums
    -0.14
    ILT
    -0.14
    Attempting
    -0.14
    ecs
    -0.14
    ori
    -0.14
    POSITIVE LOGITS
    ussen
    0.16
    çı
    0.14
     Za
    0.14
    å¾
    0.14
     actionTypes
    0.14
    masked
    0.14
     Newman
    0.13
    lica
    0.13
    _letter
    0.13
     Bord
    0.13
    Act Density 0.010%

    No Known Activations