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

    Neuronpedia

    INDEX
    Explanations

    concepts related to personal integrity and ethical principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĤÑĮ
    -0.15
     Hindered
    -0.15
     Cascade
    -0.14
    ship
    -0.14
    atures
    -0.14
    pline
    -0.13
     lightweight
    -0.13
     Ventura
    -0.13
    Seattle
    -0.13
    chan
    -0.13
    POSITIVE LOGITS
    oui
    0.16
    riminal
    0.15
    森
    0.14
    lÃŃn
    0.14
     YYS
    0.14
    ahi
    0.14
    .wrap
    0.13
    ë²Į
    0.13
    aligned
    0.13
    zin
    0.13
    Act Density 0.601%

    No Known Activations