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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to social behavior and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardown
    -0.17
    оÑĢони
    -0.16
    avo
    -0.15
    iego
    -0.14
    .tc
    -0.14
    еÑĢк
    -0.14
    ómo
    -0.14
    afort
    -0.13
    Animating
    -0.13
    EOF
    -0.13
    POSITIVE LOGITS
     when
    0.45
    when
    0.39
     whenever
    0.33
     cuando
    0.33
     quando
    0.33
    _when
    0.31
     When
    0.31
    When
    0.31
     WHEN
    0.31
     когда
    0.28
    Act Density 0.201%

    No Known Activations