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

    Neuronpedia

    INDEX
    Explanations

    policy-related statements and government proposals

    oai_token-act-pair · gpt-3.5-turbo

    phrasal structures indicating consensus and collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itarian
    -0.70
    gling
    -0.65
    iple
    -0.65
    quished
    -0.64
    Scroll
    -0.63
    iatus
    -0.63
    perture
    -0.63
    osphere
    -0.62
    agram
    -0.62
    asma
    -0.60
    POSITIVE LOGITS
     preferably
    1.35
     regardless
    1.09
    rather
    1.06
     irrespective
    1.06
     lest
    1.05
     ideally
    1.01
     ensuring
    0.97
     rather
    0.97
     wherever
    0.96
     responsibly
    0.91
    Act Density 0.302%

    No Known Activations