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

    Neuronpedia

    INDEX
    Explanations

    conjunctions connecting phrases or clauses

    oai_token-act-pair · gpt-3.5-turbo

    the presence of document delimiters or markers indicating the start and end of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bub
    -0.53
     ÂŃ
    -0.52
    —-
    -0.51
    .*
    -0.50
     hard
    -0.49
     uncont
    -0.48
    hub
    -0.48
     legally
    -0.48
    .#
    -0.47
     campaign
    -0.47
    POSITIVE LOGITS
    romeda
    1.05
    rew
    1.01
    rogens
    0.97
    ERSON
    0.94
    rogen
    0.87
    rost
    0.72
    rea
    0.71
     secondly
    0.70
    alus
    0.70
    then
    0.69
    Act Density 0.065%

    No Known Activations