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

    Neuronpedia

    INDEX
    Explanations

    terms related to policies, issues, and organizations prefixed with 'anti-'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anti-poverty or anti-corruption themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dots
    -0.69
     tuned
    -0.67
    éĹĺ
    -0.64
     notebooks
    -0.64
     mit
    -0.63
     snug
    -0.62
     srfAttach
    -0.62
    LESS
    -0.62
    staking
    -0.61
     (~
    -0.60
    POSITIVE LOGITS
    usterity
    0.97
    xiety
    0.87
    amation
    0.80
    otic
    0.80
    otics
    0.79
    amacare
    0.78
    ellectual
    0.78
    aphael
    0.74
    roleum
    0.74
    nesty
    0.72
    Act Density 0.059%

    No Known Activations