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

    Neuronpedia

    INDEX
    Explanations

    phrases related to context and settings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to context and context-oriented content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iev
    -0.77
    illet
    -0.70
    quished
    -0.69
    KK
    -0.67
    venge
    -0.67
    oshenko
    -0.67
    axe
    -0.66
    aroo
    -0.66
    gged
    -0.65
    bt
    -0.65
    POSITIVE LOGITS
    ellar
    0.76
     conve
    0.68
     Eucl
    0.65
    clus
    0.64
    tyard
    0.64
     porous
    0.60
     boundaries
    0.59
     contrasts
    0.59
    taboola
    0.59
     veins
    0.58
    Act Density 0.626%

    No Known Activations