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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acific
    -0.18
    ensch
    -0.15
     JpaRepository
    -0.15
    openh
    -0.14
    agher
    -0.14
    lez
    -0.14
    prox
    -0.14
    олÑİ
    -0.14
    .joda
    -0.14
    itre
    -0.14
    POSITIVE LOGITS
    /+
    0.31
    webkit
    0.29
    ve
    0.23
    moz
    0.18
    _-
    0.17
     sign
    0.17
    ~-~-
    0.17
    ~-~-~-~-
    0.17
    ades
    0.17
    +-+-
    0.17
    Act Density 0.083%

    No Known Activations