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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific names or identifiers related to people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quina
    -0.15
     exp
    -0.14
    cri
    -0.14
    708
    -0.14
    irk
    -0.13
     PUR
    -0.13
    kili
    -0.13
    ounded
    -0.13
    bee
    -0.12
     sinks
    -0.12
    POSITIVE LOGITS
    ıi
    0.17
    umbed
    0.17
    еди
    0.15
    abase
    0.15
     Eastern
    0.14
    vÃŃm
    0.14
     Bearings
    0.14
    ÑĥлÑİ
    0.14
    agers
    0.14
    iton
    0.13
    Act Density 0.517%

    No Known Activations