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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with "After" indicating a sequence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vu
    -0.18
    hoa
    -0.17
    uters
    -0.16
    енка
    -0.15
    ancel
    -0.15
    annis
    -0.15
    onic
    -0.15
    ç§
    -0.14
    aco
    -0.14
    nk
    -0.14
    POSITIVE LOGITS
    ward
    0.21
    IDGE
    0.16
    iated
    0.15
    wards
    0.15
    ida
    0.15
    OTH
    0.14
    incinn
    0.14
    иÑĢов
    0.14
    ilia
    0.14
    word
    0.14
    Act Density 0.067%

    No Known Activations