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

    Neuronpedia

    INDEX
    Explanations

    phrases related to showing support or allegiance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the concept of standing by or supporting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GV
    -0.73
    ivia
    -0.71
    NS
    -0.70
    ayne
    -0.68
    NT
    -0.67
    asy
    -0.66
    ilib
    -0.65
    ache
    -0.63
    YR
    -0.62
    ioxide
    -0.62
    POSITIVE LOGITS
    akuya
    0.87
     virtue
    0.84
    laws
    0.83
    products
    0.83
    product
    0.74
    iversary
    0.72
     sidelines
    0.72
    stand
    0.70
     proxy
    0.64
    roads
    0.62
    Act Density 0.050%

    No Known Activations