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

    Neuronpedia

    INDEX
    Explanations

    structural components of narratives or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zug
    -0.15
    ogui
    -0.14
    ÅĻev
    -0.14
    ------+------+
    -0.14
    ла
    -0.14
    anko
    -0.14
    iveau
    -0.14
    argo
    -0.14
    rgan
    -0.14
    _shapes
    -0.13
    POSITIVE LOGITS
     why
    0.19
     part
    0.18
     reason
    0.17
     Territory
    0.17
    ttl
    0.17
     what
    0.16
     territory
    0.15
     parte
    0.15
     μÎŃÏģοÏĤ
    0.15
    illisecond
    0.15
    Act Density 0.050%

    No Known Activations