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

    Neuronpedia

    INDEX
    Explanations

    references to news organizations and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numbered
    -0.16
    ziej
    -0.14
    metatable
    -0.14
    ekyll
    -0.14
    638
    -0.14
    ATUS
    -0.14
    uman
    -0.14
    essim
    -0.14
    atus
    -0.13
    annie
    -0.13
    POSITIVE LOGITS
     terminals
    0.18
     Bloomberg
    0.17
    rupa
    0.16
     Terminal
    0.16
     Tic
    0.16
    社
    0.15
    ody
    0.15
    oleans
    0.15
    quiv
    0.15
     Quint
    0.15
    Act Density 0.006%

    No Known Activations