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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or conjunctions within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.78
    meet
    -0.69
    UC
    -0.68
    ANC
    -0.66
     BCC
    -0.66
    Student
    -0.65
    panel
    -0.63
    Deploy
    -0.63
    WORK
    -0.62
    coal
    -0.62
    POSITIVE LOGITS
     THEN
    0.95
     blah
    0.87
     stuff
    0.84
     then
    0.83
     thus
    0.82
    romeda
    0.81
     therefore
    0.80
     thats
    0.80
     vice
    0.74
     everything
    0.74
    Act Density 0.562%

    No Known Activations