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

    Neuronpedia

    INDEX
    Explanations

    information related to research papers and publications

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas in lists or complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.77
    robe
    -0.65
    Russ
    -0.60
    STON
    -0.60
    ,—
    -0.60
    ,
    -0.59
     (>
    -0.59
    Standing
    -0.52
    zbek
    -0.52
     shenan
    -0.51
    POSITIVE LOGITS
     consists
    1.05
     comprises
    1.01
     revolves
    0.99
     involves
    0.99
     is
    0.96
     represents
    0.96
     contains
    0.95
     relies
    0.95
     has
    0.94
     provides
    0.93
    Act Density 0.155%

    No Known Activations