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

    Neuronpedia

    INDEX
    Explanations

    phrases related to highlighting differences or distinctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to distinctions or differentiations between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vae
    -0.76
    annis
    -0.73
    rollers
    -0.72
    onz
    -0.68
    odes
    -0.63
     Polo
    -0.62
    ctic
    -0.60
     paran
    -0.59
    ODE
    -0.58
    reens
    -0.58
    POSITIVE LOGITS
    naire
    1.02
     distinction
    0.89
    abl
    0.88
    erence
    0.88
     distinctions
    0.83
    otomy
    0.83
    yip
    0.79
    xual
    0.79
    ovan
    0.77
    alities
    0.77
    Act Density 0.019%

    No Known Activations