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

    Neuronpedia

    INDEX
    Explanations

    contractions and informal phrases that emphasize strong emotions or attitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _TUN
    -0.15
     millis
    -0.15
    Ymd
    -0.14
    anut
    -0.14
     Saunders
    -0.14
     speaking
    -0.14
     tun
    -0.14
    ÑģоÑĤ
    -0.13
    omy
    -0.13
     captive
    -0.13
    POSITIVE LOGITS
    enza
    0.16
    onym
    0.15
    irth
    0.15
    trs
    0.15
    iline
    0.15
    ipsis
    0.14
    ewood
    0.14
    žel
    0.14
    etes
    0.14
     trig
    0.14
    Act Density 0.000%

    No Known Activations