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

    Neuronpedia

    INDEX
    Explanations

    references to "ponies" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esk
    -0.18
    enaire
    -0.16
    heet
    -0.16
    uset
    -0.16
    auga
    -0.15
    éĢĢ
    -0.15
    erç
    -0.15
    วà¸ĩ
    -0.15
    esium
    -0.15
    orgia
    -0.15
    POSITIVE LOGITS
     pon
    0.21
    pon
    0.18
    pons
    0.17
    posal
    0.16
    yp
    0.16
     Pon
    0.16
    ŀĭ
    0.16
    yc
    0.16
    apon
    0.15
     material
    0.14
    Act Density 0.010%

    No Known Activations