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

    Neuronpedia

    INDEX
    Explanations

    words and phrases denoting locations and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼ķãģį
    -0.14
    lek
    -0.14
    ving
    -0.14
    apan
    -0.14
    anton
    -0.14
    utz
    -0.14
    arning
    -0.13
    код
    -0.13
    asm
    -0.13
    abelle
    -0.13
    POSITIVE LOGITS
     level
    0.24
     detriment
    0.23
     moment
    0.21
     expense
    0.20
     sein
    0.19
     expenses
    0.17
    aise
    0.16
    expense
    0.16
     pied
    0.16
    ubre
    0.16
    Act Density 0.016%

    No Known Activations