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

    Neuronpedia

    INDEX
    Explanations

    references to children's literature and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    locs
    -0.15
    ูà¸ķ
    -0.15
    >manual
    -0.14
     Valve
    -0.14
    ocalypse
    -0.14
    _shuffle
    -0.14
    owment
    -0.14
    .exchange
    -0.13
    swick
    -0.13
    è¨
    -0.13
    POSITIVE LOGITS
     DK
    0.25
    DK
    0.24
     facts
    0.20
     Fact
    0.19
     inf
    0.19
    Fact
    0.19
     Facts
    0.17
     fact
    0.17
    fact
    0.17
    dk
    0.17
    Act Density 0.025%

    No Known Activations