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

    Neuronpedia

    INDEX
    Explanations

    references to time and temporal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.18
    rego
    -0.16
     doc
    -0.15
     overnight
    -0.15
     Kund
    -0.15
     ap
    -0.15
    ัà¹ī
    -0.14
     вол
    -0.14
    lic
    -0.14
     sed
    -0.14
    POSITIVE LOGITS
    pek
    0.17
    zcze
    0.16
    æ³
    0.16
    pch
    0.16
    ometown
    0.15
     ragaz
    0.15
     bacheca
    0.14
    BindingUtil
    0.14
    ileaks
    0.14
    ossier
    0.14
    Act Density 0.039%

    No Known Activations