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

    Neuronpedia

    INDEX
    Explanations

    descriptions of architectural elements and their surroundings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¡ļ
    -0.14
    ouri
    -0.14
    ç¯
    -0.13
     Loft
    -0.13
    Presence
    -0.13
    eks
    -0.13
    รายà¸ģาร
    -0.13
    837
    -0.13
    enia
    -0.13
    able
    -0.12
    POSITIVE LOGITS
     behind
    0.26
     beneath
    0.23
    Behind
    0.23
     Behind
    0.23
     underneath
    0.20
     opposite
    0.20
    Inside
    0.20
    inside
    0.19
     inside
    0.19
     Bene
    0.19
    Act Density 0.155%

    No Known Activations