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

    Neuronpedia

    INDEX
    Explanations

    The neuron is looking for words related to political figures and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    connective phrases and conjunctions that indicate relationships or transitions between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¢
    -0.74
    orthy
    -0.65
    taker
    -0.64
    lein
    -0.63
    uria
    -0.62
    omal
    -0.62
    imester
    -0.61
    pee
    -0.61
    rison
    -0.60
    myra
    -0.60
    POSITIVE LOGITS
    etc
    1.55
    whatever
    1.25
     blah
    1.06
     whatever
    1.05
     etc
    0.94
     assorted
    0.93
     everything
    0.91
     whichever
    0.89
     respectively
    0.85
    anything
    0.84
    Act Density 0.195%

    No Known Activations