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

    Neuronpedia

    INDEX
    Explanations

    references to existential questions and the concept of suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.15
    TS
    -0.15
     Leone
    -0.14
    ernel
    -0.14
    cce
    -0.14
    olls
    -0.14
    ubi
    -0.14
    جÙĬÙĦ
    -0.14
    ÙĦÙĬÙĩ
    -0.13
    ongo
    -0.13
    POSITIVE LOGITS
    fen
    0.17
     depth
    0.15
    aton
    0.15
    apes
    0.15
    aise
    0.14
    lam
    0.14
    645
    0.14
     circ
    0.14
    inson
    0.14
     depths
    0.14
    Act Density 0.002%

    No Known Activations