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

    Neuronpedia

    INDEX
    Explanations

    elements related to configuration settings and flags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     st
    -0.16
     comple
    -0.15
     Constit
    -0.14
    isses
    -0.14
    annon
    -0.14
     ben
    -0.14
    abin
    -0.14
     Ike
    -0.14
    /commons
    -0.14
     Magn
    -0.13
    POSITIVE LOGITS
    cheng
    0.17
    adder
    0.16
     Skin
    0.15
    _skin
    0.15
    atz
    0.15
    -dot
    0.14
    æ¶
    0.14
    IGO
    0.14
    endid
    0.14
     Rudd
    0.14
    Act Density 0.081%

    No Known Activations