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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quality or reputation, particularly the term "well-known."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .major
    -0.15
    cem
    -0.15
    kı
    -0.15
    ic
    -0.14
    yd
    -0.14
    olit
    -0.14
     Olsen
    -0.14
    InputLabel
    -0.14
    noop
    -0.14
    oser
    -0.14
    POSITIVE LOGITS
    ington
    0.26
    spring
    0.20
    -known
    0.20
    INGTON
    0.19
     intention
    0.18
     known
    0.17
     timed
    0.17
    fare
    0.16
     well
    0.16
    ness
    0.16
    Act Density 0.029%

    No Known Activations