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

    Neuronpedia

    INDEX
    Explanations

    dates and references to years and significant time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reagan
    -0.16
    éİ
    -0.15
     Thatcher
    -0.15
    /bower
    -0.15
    ilton
    -0.15
    ierz
    -0.14
     McM
    -0.14
    ÑģÑĥÑĤ
    -0.14
    etak
    -0.14
     Canter
    -0.14
    POSITIVE LOGITS
    200
    0.66
    Û²Û°Û°
    0.49
     Bush
    0.40
     bush
    0.36
    Bush
    0.30
    २०
    0.25
    300
    0.21
    400
    0.19
    00
    0.17
    Û±Û³Û¸
    0.17
    Act Density 0.127%

    No Known Activations