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

    Neuronpedia

    INDEX
    Explanations

    instances where rules or violations are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal or regulatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uador
    -0.55
    DragonMagazine
    -0.54
    bably
    -0.53
    ©¶æ
    -0.52
    akespeare
    -0.49
     Architects
    -0.47
    ventus
    -0.47
    ĸļ
    -0.46
    icho
    -0.45
    ibaba
    -0.45
    POSITIVE LOGITS
    .?
    1.29
    .(
    1.23
    .
    1.23
    !.
    1.22
    .</
    1.19
    .'
    1.17
    .�
    1.16
     anymore
    1.14
    %.
    1.12
    .–
    1.12
    Act Density 1.441%

    No Known Activations