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

    Neuronpedia

    INDEX
    Explanations

    elements related to power dynamics and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loh
    -0.16
    olina
    -0.16
    аÑĢан
    -0.16
    lan
    -0.15
    Nib
    -0.15
     brill
    -0.15
    Fcn
    -0.15
     Wahl
    -0.15
    171
    -0.14
    731
    -0.14
    POSITIVE LOGITS
     Å
    0.18
     wy
    0.18
    ificacion
    0.17
     sond
    0.17
    bih
    0.17
    Å©
    0.15
    vail
    0.15
     rych
    0.15
    adow
    0.15
     Estr
    0.15
    Act Density 0.014%

    No Known Activations