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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and events taking place simultaneously

    oai_token-act-pair · gpt-3.5-turbo

    the word "while" and its variations used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elled
    -0.77
    aer
    -0.73
     fuse
    -0.73
    atron
    -0.70
    ibaba
    -0.67
    orb
    -0.66
    ellen
    -0.66
    ulous
    -0.66
    urious
    -0.66
    ordes
    -0.66
    POSITIVE LOGITS
     browsing
    0.99
     researching
    0.87
     discussing
    0.82
     acknowledging
    0.81
     respecting
    0.79
     listening
    0.78
     touring
    0.78
     watching
    0.76
     ignoring
    0.75
     airing
    0.75
    Act Density 0.063%

    No Known Activations