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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akens
    -0.17
     بت
    -0.16
    enko
    -0.15
    :"-"`↵
    -0.15
    trx
    -0.15
    thal
    -0.14
     Gas
    -0.14
    ing
    -0.14
    ******/
    -0.13
     Trilogy
    -0.13
    POSITIVE LOGITS
    POCH
    0.17
    inned
    0.16
    oting
    0.15
    _RANK
    0.15
    abo
    0.14
     urn
    0.14
    dou
    0.14
    ][_
    0.14
     cresc
    0.13
     Sweep
    0.13
    Act Density 0.005%

    No Known Activations