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

    Neuronpedia

    INDEX
    Explanations

    characters with strong emotional connections or significant interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äħd
    -0.17
    殿
    -0.16
    iers
    -0.15
     hierarchy
    -0.14
    ictions
    -0.14
    ThanOr
    -0.14
    oyer
    -0.14
    аÑĢам
    -0.14
    ové
    -0.14
    owo
    -0.14
    POSITIVE LOGITS
    ames
    0.28
    akes
    0.26
    agh
    0.26
    ashtra
    0.25
    ishi
    0.24
    ajs
    0.24
    enu
    0.23
    aja
    0.22
    uchi
    0.22
    AMES
    0.21
    Act Density 0.034%

    No Known Activations