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

    Neuronpedia

    INDEX
    Explanations

    references to organizational affiliations and communal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FFFFFFFF
    -0.17
     Municip
    -0.15
    raq
    -0.15
    -spinner
    -0.14
    ControlEvents
    -0.14
    sov
    -0.14
    _ra
    -0.14
     двоÑĢ
    -0.13
    ibbon
    -0.13
     Vince
    -0.13
    POSITIVE LOGITS
     conference
    0.29
     Conference
    0.29
     conferences
    0.25
    conference
    0.25
    Conference
    0.24
     Annual
    0.23
     Connection
    0.22
     UM
    0.22
     Method
    0.21
     ep
    0.21
    Act Density 0.013%

    No Known Activations