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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exploration and in-depth analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    overn
    -0.16
    ograms
    -0.16
    arian
    -0.16
    oded
    -0.15
    паÑĤ
    -0.15
    ouched
    -0.14
     Hava
    -0.14
     Yak
    -0.14
    ICTURE
    -0.14
    obra
    -0.13
    POSITIVE LOGITS
     deeper
    0.43
     deep
    0.41
    deep
    0.35
     into
    0.35
     deepest
    0.34
     Deep
    0.32
     depths
    0.31
    Deep
    0.30
     deeply
    0.29
     sâu
    0.29
    Act Density 0.020%

    No Known Activations