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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss methods or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernet
    -0.18
    shaw
    -0.15
    aret
    -0.14
    ern
    -0.14
    [char
    -0.14
    han
    -0.14
    Æ°Æ¡ng
    -0.14
    Įĵ
    -0.13
    /md
    -0.13
     मद
    -0.13
    POSITIVE LOGITS
    tgt
    0.15
    iker
    0.15
    ertiary
    0.15
    kker
    0.14
    λοÏħ
    0.14
    ptic
    0.13
    orthand
    0.13
    urtles
    0.13
    reak
    0.13
    292
    0.13
    Act Density 0.039%

    No Known Activations