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

    Neuronpedia

    INDEX
    Explanations

    instances of conversational transitions and rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĩº
    -0.16
    uns
    -0.15
    ork
    -0.15
     Dough
    -0.14
    220
    -0.14
    lava
    -0.14
    berg
    -0.14
    avig
    -0.14
     Housing
    -0.14
    arn
    -0.13
    POSITIVE LOGITS
    _gap
    0.19
    ãĤıãģĽ
    0.16
    ãĥ¥
    0.15
    -gap
    0.15
     DISCLAIM
    0.14
    ì±ħ
    0.14
    Gap
    0.14
    chy
    0.14
    EPROM
    0.14
    eka
    0.14
    Act Density 0.061%

    No Known Activations