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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time-related changes or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mie
    -0.15
    inho
    -0.15
    ÏĥÏħ
    -0.15
    esan
    -0.14
     rotterdam
    -0.14
    ">//
    -0.14
    854
    -0.14
    /Branch
    -0.14
    umble
    -0.13
    ाà¤Ĭ
    -0.13
    POSITIVE LOGITS
     Strange
    0.17
     Unexpected
    0.16
     especially
    0.16
     normally
    0.16
    olina
    0.15
    Unexpected
    0.15
     unusual
    0.15
     anom
    0.15
    omain
    0.15
     unexpected
    0.15
    Act Density 0.002%

    No Known Activations