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

    Neuronpedia

    INDEX
    Explanations

    code-related elements or constructs, particularly those involving class instances and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Presidency
    -0.14
    brief
    -0.14
    elden
    -0.13
     presidency
    -0.13
     Wid
    -0.13
     Pf
    -0.13
     nonatomic
    -0.13
    ohl
    -0.13
    rip
    -0.13
     imaginable
    -0.12
    POSITIVE LOGITS
    ERO
    0.15
    les
    0.15
    abay
    0.14
    ORITY
    0.14
    tery
    0.14
    .SDK
    0.14
    llib
    0.14
    sse
    0.14
    erot
    0.13
    _UNUSED
    0.13
    Act Density 0.010%

    No Known Activations