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

    Neuronpedia

    INDEX
    Explanations

    numerical data or metrics related to studies or research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ump
    -0.15
    imest
    -0.14
    187
    -0.14
     Hlav
    -0.13
     anc
    -0.13
     minority
    -0.13
    ulong
    -0.13
    جاÙħ
    -0.13
    anc
    -0.13
    esta
    -0.13
    POSITIVE LOGITS
    dish
    0.19
    à¤Ĥधन
    0.15
    quina
    0.15
     Lives
    0.15
    оÑĢод
    0.14
    "crypto
    0.14
    ather
    0.14
     lives
    0.13
    ends
    0.13
    represent
    0.13
    Act Density 0.012%

    No Known Activations