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

    Neuronpedia

    INDEX
    Explanations

    specific years, particularly referring to the year 201, along with expressions indicating identity or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akan
    -0.17
    kowski
    -0.16
     Shut
    -0.15
    igi
    -0.15
     shutting
    -0.15
     Roberts
    -0.15
    ÅŁt
    -0.15
    ako
    -0.15
    _git
    -0.15
     shut
    -0.14
    POSITIVE LOGITS
    orda
    0.16
    atri
    0.15
    atr
    0.15
    AT
    0.15
     Lawson
    0.15
    ounc
    0.15
    ogi
    0.14
    ÑĤÑĢи
    0.14
    AdapterFactory
    0.14
     Athen
    0.14
    Act Density 0.036%

    No Known Activations