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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding and acquiring knowledge or skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    260
    -0.15
     experienced
    -0.14
    352
    -0.14
    _defs
    -0.14
     phi
    -0.14
     Experienced
    -0.14
    logan
    -0.14
    ibar
    -0.14
    öst
    -0.13
    baum
    -0.13
    POSITIVE LOGITS
     knowledge
    0.67
    knowledge
    0.58
     Knowledge
    0.54
    Knowledge
    0.51
     understanding
    0.47
    çŁ¥è¯Ĩ
    0.43
     awareness
    0.38
     Understanding
    0.37
    nowledge
    0.35
     conosc
    0.35
    Act Density 0.216%

    No Known Activations