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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning the concept of the future and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esses
    -0.17
    acl
    -0.16
    down
    -0.16
    ola
    -0.15
    laus
    -0.15
    ories
    -0.14
    ady
    -0.14
    abeth
    -0.14
    ãĥ«ãĥĪ
    -0.14
    otos
    -0.14
    POSITIVE LOGITS
    ktop
    0.16
    weis
    0.15
    imar
    0.15
    aneously
    0.15
    ãĤ¹ãĥŀ
    0.15
    qué
    0.15
    /current
    0.15
    greens
    0.14
    -proof
    0.14
    imary
    0.14
    Act Density 0.029%

    No Known Activations