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

    Neuronpedia

    INDEX
    Explanations

    phrases related to breaks or interruptions in regular activities

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative breaks or pauses in sessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reply
    -0.66
    gged
    -0.63
    da
    -0.61
    foot
    -0.60
    cas
    -0.60
    DK
    -0.60
    nington
    -0.60
    source
    -0.60
    cknowled
    -0.59
     Solo
    -0.59
    POSITIVE LOGITS
     recess
    1.64
    engers
    0.92
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.85
    es
    0.85
    icut
    0.84
    ively
    0.83
    ioned
    0.83
    atile
    0.82
    ional
    0.82
    ecast
    0.79
    Act Density 0.003%

    No Known Activations