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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that stand out as important or significant

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "highlighted"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opic
    -0.75
    proxy
    -0.72
    wives
    -0.71
    cible
    -0.71
    cas
    -0.66
    wife
    -0.65
    appro
    -0.64
    eties
    -0.63
    atell
    -0.63
    hold
    -0.63
    POSITIVE LOGITS
     highlighted
    0.85
    ocument
    0.84
    umenthal
    0.78
     highlighting
    0.76
    TextColor
    0.74
    OWS
    0.72
     prominently
    0.70
     warnings
    0.69
     contrasting
    0.69
     highlights
    0.67
    Act Density 0.016%

    No Known Activations