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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing positive attributes or features

    oai_token-act-pair · gpt-3.5-turbo

    descriptors and adjectives related to quality and experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sama
    -0.74
    udeb
    -0.71
    ãģ®æ
    -0.71
    aucus
    -0.70
    imester
    -0.69
    uphem
    -0.69
    ©¶æ
    -0.69
    utenant
    -0.68
     blamed
    -0.67
    phrine
    -0.67
    POSITIVE LOGITS
     visuals
    0.88
     outdoor
    0.82
     handmade
    0.81
     yet
    0.81
    ly
    0.80
     interactive
    0.79
     multimedia
    0.77
     interior
    0.77
     artwork
    0.76
    LY
    0.75
    Act Density 0.259%

    No Known Activations