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

    Neuronpedia

    INDEX
    Explanations

    references to user privacy and data usage policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uria
    -0.16
     facult
    -0.14
    nier
    -0.14
    assis
    -0.14
    460
    -0.14
    raman
    -0.14
    nants
    -0.14
    anton
    -0.13
    rier
    -0.13
    672
    -0.13
    POSITIVE LOGITS
    adows
    0.16
    poz
    0.15
    abella
    0.15
    .plus
    0.14
     ë¹Ī
    0.14
    acher
    0.14
    adele
    0.14
    oref
    0.14
     Zu
    0.14
    .easing
    0.14
    Act Density 0.006%

    No Known Activations