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

    Neuronpedia

    INDEX
    Explanations

    instances of personal opinion or belief statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hausen
    -0.16
    rů
    -0.15
     ëĭµ
    -0.15
    OpenHelper
    -0.15
     mocker
    -0.14
    eldon
    -0.14
    zenia
    -0.14
    omal
    -0.13
    unction
    -0.13
    pects
    -0.13
    POSITIVE LOGITS
     Captain
    0.16
    -ie
    0.16
     Hook
    0.15
    andom
    0.15
    島
    0.14
    _HOOK
    0.14
    ÑĨеп
    0.13
    polator
    0.13
     Company
    0.13
    insula
    0.13
    Act Density 0.000%

    No Known Activations