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

    Neuronpedia

    INDEX
    Explanations

    references to entities or organizations, particularly those abbreviated with 'N'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ote
    -0.20
    lose
    -0.19
    -animation
    -0.17
    ighton
    -0.17
    UMP
    -0.16
    arias
    -0.15
    Ñĥда
    -0.15
    eway
    -0.15
    oris
    -0.15
    ode
    -0.15
    POSITIVE LOGITS
    iles
    0.18
    fleet
    0.16
     orth
    0.15
    wand
    0.15
    Orth
    0.15
    atic
    0.15
    apa
    0.15
    tuk
    0.15
    CLUDE
    0.15
    CS
    0.14
    Act Density 0.035%

    No Known Activations