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

    Neuronpedia

    INDEX
    Explanations

    comparisons or similarities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a sense of approximation or near-ness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oran
    -0.82
    agate
    -0.80
     Dynamics
    -0.70
    Ds
    -0.70
    oris
    -0.70
     è£ıè¦ļéĨĴ
    -0.65
    eria
    -0.65
     RTX
    -0.64
    ourses
    -0.64
    Ey
    -0.64
    POSITIVE LOGITS
     certainly
    0.80
    stress
    0.71
    etheless
    0.70
     identical
    0.70
     mundane
    0.68
    yrinth
    0.65
    rito
    0.63
    olkien
    0.63
     exclusively
    0.63
    arser
    0.63
    Act Density 0.034%

    No Known Activations