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

    Neuronpedia

    INDEX
    Explanations

    references to underground structures and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    het
    -0.15
    мом
    -0.15
    å·±
    -0.15
    ÑģÑĤеÑĢ
    -0.14
    emale
    -0.14
    /*----------------------------------------------------------------------------
    -0.14
    çŃĭ
    -0.14
    atan
    -0.14
    ç±
    -0.13
    ÙĪÙĨØ©
    -0.13
    POSITIVE LOGITS
     depths
    0.18
     bur
    0.18
     beneath
    0.17
     deepest
    0.17
    室
    0.17
     depth
    0.16
    arda
    0.16
     bulk
    0.16
     underground
    0.15
    _depth
    0.14
    Act Density 0.093%

    No Known Activations