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

    Neuronpedia

    INDEX
    Explanations

    references to user profiles and personal information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oral
    -0.16
    reich
    -0.16
    reas
    -0.16
    ارÙĬØ®
    -0.16
    olves
    -0.15
    rena
    -0.15
    rei
    -0.15
    falls
    -0.15
    ENO
    -0.14
    że
    -0.14
    POSITIVE LOGITS
    /profile
    0.24
    lla
    0.20
    d
    0.20
    matic
    0.18
    .Profile
    0.18
    tte
    0.17
    stown
    0.17
    (Profile
    0.16
    ty
    0.16
    thane
    0.16
    Act Density 0.018%

    No Known Activations