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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is expressing support or enthusiasm for a particular idea or action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal support or commitment to causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.77
     allegedly
    -0.67
    NZ
    -0.66
     respectively
    -0.66
     Autob
    -0.65
    their
    -0.65
    ranged
    -0.63
    Their
    -0.62
    ERE
    -0.58
     Hebdo
    -0.58
    POSITIVE LOGITS
     myself
    1.58
     my
    0.96
    poke
    0.74
    aido
    0.71
    uno
    0.69
     Patreon
    0.69
    76561
    0.66
    minist
    0.64
    ividual
    0.63
     paraph
    0.63
    Act Density 0.817%

    No Known Activations