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

    Neuronpedia

    INDEX
    Explanations

    terms related to organizational structure and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chner
    -0.15
    orget
    -0.14
    ityEngine
    -0.14
    olls
    -0.14
     Bold
    -0.14
     nothing
    -0.13
    ffen
    -0.13
    à¹Ģà¸Ł
    -0.13
    894
    -0.13
    hem
    -0.13
    POSITIVE LOGITS
    -wide
    0.50
    -specific
    0.49
    -level
    0.48
    wide
    0.47
     specific
    0.40
    pecific
    0.40
     wide
    0.39
     level
    0.38
    specific
    0.38
    _specific
    0.37
    Act Density 0.347%

    No Known Activations