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

    Neuronpedia

    INDEX
    Explanations

    key structural elements and thematic concepts in discussions or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apa
    -0.16
     like
    -0.16
    ifo
    -0.15
    hea
    -0.15
     ways
    -0.14
    isman
    -0.14
    olog
    -0.14
    оÑĩкÑĥ
    -0.14
    anders
    -0.14
    istr
    -0.14
    POSITIVE LOGITS
    liest
    0.20
    iest
    0.20
     choice
    0.20
    choice
    0.20
     duy
    0.18
    Choice
    0.17
     franca
    0.16
    ropoda
    0.16
    _choice
    0.16
     equivalent
    0.16
    Act Density 0.221%

    No Known Activations