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

    Neuronpedia

    INDEX
    Explanations

    references to kidnapping and abduction incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rup
    -0.16
    ppo
    -0.15
    amet
    -0.14
     Rew
    -0.14
    773
    -0.14
    quential
    -0.14
    ulen
    -0.14
    _TYPED
    -0.14
    ika
    -0.14
    EPROM
    -0.13
    POSITIVE LOGITS
    cript
    0.20
    atron
    0.17
    orum
    0.16
    urette
    0.15
    istani
    0.15
    Äĩe
    0.15
    oppers
    0.14
     aver
    0.14
     Tobias
    0.14
    elic
    0.14
    Act Density 0.012%

    No Known Activations