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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives highlighting complexity and artistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     own
    -0.17
    nten
    -0.15
    aven
    -0.15
    ogn
    -0.14
    NI
    -0.14
     nick
    -0.13
    åŃĿ
    -0.13
    venting
    -0.13
    οÏĤ
    -0.13
    кÑģ
    -0.13
    POSITIVE LOGITS
     nature
    0.28
    nature
    0.21
     Nature
    0.17
    washer
    0.16
    iflower
    0.15
    NESS
    0.15
    ness
    0.15
    ãĤ¤ãĥ¤
    0.15
    _EMIT
    0.15
    γον
    0.15
    Act Density 0.373%

    No Known Activations