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

    Neuronpedia

    INDEX
    Explanations

    expressions of potential outcomes and dependencies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijo
    -0.17
    obar
    -0.15
    heid
    -0.15
    alic
    -0.15
    ensa
    -0.15
    ä¸Ģ度
    -0.15
    å°¾
    -0.14
    ultan
    -0.14
     known
    -0.13
    tl
    -0.13
    POSITIVE LOGITS
    TYPES
    0.15
    SOR
    0.15
    azon
    0.15
     sor
    0.15
    CTOR
    0.14
    arrow
    0.14
    214
    0.14
     Cummings
    0.14
     solar
    0.13
     Chun
    0.13
    Act Density 0.019%

    No Known Activations