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

    Neuronpedia

    INDEX
    Explanations

    references to honors and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vette
    -0.17
    ENDING
    -0.15
    eer
    -0.15
    hoot
    -0.15
    een
    -0.15
    otty
    -0.15
    æĪ¸
    -0.15
    e
    -0.15
    ennial
    -0.14
     Ri
    -0.14
    POSITIVE LOGITS
    orary
    0.34
    ours
    0.32
    orable
    0.29
    olulu
    0.27
    ored
    0.27
    esty
    0.26
    oured
    0.25
    oring
    0.23
    ors
    0.23
    OURS
    0.21
    Act Density 0.005%

    No Known Activations