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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and concepts related to improvement and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzz
    -0.16
    reta
    -0.15
    aran
    -0.14
    UNCH
    -0.14
    sburg
    -0.14
    aser
    -0.14
    unch
    -0.14
    scope
    -0.13
    arm
    -0.13
    kins
    -0.13
    POSITIVE LOGITS
    ocale
    0.16
    üm
    0.15
     bills
    0.15
    üre
    0.14
    oci
    0.14
    vro
    0.14
     UA
    0.14
    á»ķ
    0.14
    acam
    0.14
    ourse
    0.14
    Act Density 0.021%

    No Known Activations