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

    Neuronpedia

    INDEX
    Explanations

    references to specific authors or citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anium
    -0.15
    Åį
    -0.15
    agua
    -0.14
    äft
    -0.14
    ovo
    -0.14
    uestas
    -0.14
    éru
    -0.14
    acam
    -0.14
    езда
    -0.14
     Tomáš
    -0.13
    POSITIVE LOGITS
     et
    0.29
    ̧
    0.18
    08
    0.18
    06
    0.18
    201
    0.18
    05
    0.17
    07
    0.17
    iÄĩ
    0.17
    09
    0.16
    03
    0.16
    Act Density 0.156%

    No Known Activations