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

    Neuronpedia

    INDEX
    Explanations

    references to control and governance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÐĴÐIJ
    -0.15
    ayer
    -0.14
    aye
    -0.14
    vanced
    -0.14
    ipline
    -0.14
     showers
    -0.14
    frm
    -0.14
    kon
    -0.13
    locker
    -0.13
    важ
    -0.13
    POSITIVE LOGITS
     again
    0.29
     Again
    0.23
    again
    0.22
    Again
    0.21
     AGAIN
    0.20
     åıĪ
    0.18
    abee
    0.17
     lại
    0.17
     lagi
    0.17
    AGAIN
    0.17
    Act Density 0.323%

    No Known Activations