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

    Neuronpedia

    INDEX
    Explanations

    references to the abstract concept of love and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omor
    -0.15
     turno
    -0.14
    (çģ«
    -0.13
    wish
    -0.13
     tầm
    -0.13
    ancode
    -0.13
    vern
    -0.13
    toy
    -0.13
    WH
    -0.13
    ноÑģÑıÑĤ
    -0.13
    POSITIVE LOGITS
    eldo
    0.17
    ober
    0.16
    ela
    0.15
    being
    0.15
     Voice
    0.15
    ets
    0.14
    ding
    0.14
    yum
    0.14
    ikan
    0.14
    idy
    0.14
    Act Density 0.580%

    No Known Activations