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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing beauty or attractiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     need
    -0.64
     Frankfurt
    -0.64
    matter
    -0.62
     tri
    -0.57
     Schr
    -0.56
     introduced
    -0.55
     pairs
    -0.55
     rein
    -0.55
     recon
    -0.55
     retail
    -0.55
    POSITIVE LOGITS
    iful
    4.57
    ifully
    3.31
    iless
    1.93
    eous
    1.50
    iable
    1.25
    FUL
    1.22
    ificent
    1.11
    uitous
    1.11
    ful
    1.10
    ious
    1.04
    Act Density 0.015%

    No Known Activations