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

    Neuronpedia

    INDEX
    Explanations

    discourse centered around values, beliefs, and argumentative reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meth
    -0.15
     physic
    -0.14
    nim
    -0.14
     tob
    -0.14
    elapsed
    -0.14
     duplicates
    -0.13
    adle
    -0.13
     pres
    -0.13
    intr
    -0.13
     authenticated
    -0.13
    POSITIVE LOGITS
    atee
    0.17
    TEE
    0.16
    ivid
    0.15
     FUCK
    0.15
    á»ĭ
    0.14
     nackte
    0.14
     roughly
    0.14
    atsapp
    0.14
    isches
    0.14
    æŁĵ
    0.14
    Act Density 0.012%

    No Known Activations