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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations about books and films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uml
    -0.17
    vin
    -0.15
    ruise
    -0.14
     Trey
    -0.14
    umlu
    -0.14
    amp
    -0.14
     timing
    -0.14
    ru
    -0.14
     Moreno
    -0.14
    ↵
    -0.13
    POSITIVE LOGITS
    ÑģÑĤÑĥп
    0.16
    ForEach
    0.16
    agner
    0.15
    ($('<
    0.14
    èľ
    0.14
    anke
    0.14
    stuff
    0.14
    aida
    0.14
    ë¡ľëĵľ
    0.14
    Mit
    0.14
    Act Density 0.043%

    No Known Activations