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

    Neuronpedia

    INDEX
    Explanations

    sentences ending in periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of separation or disconnection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anni
    -0.82
    ascus
    -0.81
    oun
    -0.81
     inver
    -0.80
    onga
    -0.79
    culus
    -0.77
     advoc
    -0.76
    thal
    -0.76
     nuts
    -0.76
     oun
    -0.75
    POSITIVE LOGITS
     Literally
    1.05
     Whether
    0.98
     Doctors
    0.97
     Whenever
    0.96
     Especially
    0.96
    txt
    0.94
     Sometimes
    0.93
     Neither
    0.93
     Unless
    0.92
     But
    0.92
    Act Density 0.695%

    No Known Activations