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

    Neuronpedia

    INDEX
    Explanations

    references to film and entertainment reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecurity
    -0.16
    StackTrace
    -0.15
    otron
    -0.14
    erosis
    -0.14
    elles
    -0.14
    окÑĢем
    -0.13
    emer
    -0.13
    ardash
    -0.13
     triang
    -0.13
    커ìĬ¤
    -0.13
    POSITIVE LOGITS
     heroine
    0.21
     hero
    0.20
    -hero
    0.18
     interval
    0.18
     tol
    0.17
    çıł
    0.17
     Tel
    0.16
     mass
    0.16
    ühr
    0.16
     Hero
    0.16
    Act Density 0.013%

    No Known Activations