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

    Neuronpedia

    INDEX
    Explanations

    multiple references to common names or descriptors associated with subjects in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coder
    -0.16
    enu
    -0.15
    çģ
    -0.15
    upro
    -0.14
    uples
    -0.14
    ENU
    -0.14
    à¸ģà¸ķ
    -0.14
    anches
    -0.14
    ÏĢοÏį
    -0.14
    setattr
    -0.13
    POSITIVE LOGITS
     know
    0.43
     knows
    0.40
     known
    0.31
     Know
    0.30
     conoc
    0.28
     refere
    0.28
     referred
    0.27
     refer
    0.27
    know
    0.27
     conhec
    0.27
    Act Density 0.113%

    No Known Activations