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

    Neuronpedia

    INDEX
    Explanations

    references to significant numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argo
    -0.17
    ips
    -0.14
     Stevens
    -0.14
    ASF
    -0.14
    UnitOfWork
    -0.13
    indsight
    -0.13
     heck
    -0.13
     Mej
    -0.13
    er
    -0.12
    arget
    -0.12
    POSITIVE LOGITS
    amina
    0.16
    æ¬
    0.14
    eza
    0.14
    nila
    0.14
    tm
    0.14
    czy
    0.14
    âĤ¬“
    0.14
    <dim
    0.13
    vided
    0.13
    orte
    0.13
    Act Density 0.165%

    No Known Activations