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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official procedures or announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to vote counts and roll calls in legislative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILE
    -0.78
    ãĥ¤
    -0.78
    IOR
    -0.71
    ior
    -0.71
    bub
    -0.70
    ãĤ»
    -0.70
    itably
    -0.68
    acters
    -0.68
     BaseType
    -0.65
    bour
    -0.65
    POSITIVE LOGITS
    icking
    0.91
    sheet
    0.83
    Roll
    0.78
    outs
    0.78
    aways
    0.77
    roll
    0.77
    top
    0.77
    anut
    0.77
    ers
    0.76
     oats
    0.75
    Act Density 0.033%

    No Known Activations