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

    Neuronpedia

    INDEX
    Explanations

    timely expressions that indicate the present or very recent past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.72
     himſelf
    -0.70
    LLocation
    -0.70
     whofe
    -0.69
     Chriftian
    -0.64
    <<"\
    -0.62
     Cæsar
    -0.61
    िखित
    -0.61
    ſelf
    -0.60
     themſelves
    -0.60
    POSITIVE LOGITS
     it
    0.85
    はじめに
    0.77
     we
    0.75
     there
    0.72
    SequentialGroup
    0.72
    gway
    0.72
    Somehow
    0.70
    Normally
    0.68
     they
    0.67
     оригіналу
    0.66
    Act Density 0.460%

    No Known Activations