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

    Neuronpedia

    INDEX
    Explanations

    references to important terms and concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CCI
    -0.17
    ampp
    -0.17
    hair
    -0.16
    avad
    -0.15
    ropolis
    -0.15
    odzi
    -0.15
    odge
    -0.15
    avar
    -0.15
    ocking
    -0.14
    ÑĤеÑĢи
    -0.14
    POSITIVE LOGITS
     themselves
    0.18
    ling
    0.16
    inf
    0.15
    \OptionsResolver
    0.15
    ll
    0.15
     Streams
    0.14
    Streams
    0.14
    /options
    0.14
    ack
    0.14
    ä
    0.14
    Act Density 0.724%

    No Known Activations