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

    Neuronpedia

    INDEX
    Explanations

    uses of the word "highlight" related to emphasizing, pointing out or showcasing information or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to highlighting important information or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cas
    -0.77
    itte
    -0.75
    thood
    -0.71
    hell
    -0.69
    ja
    -0.68
    onew
    -0.66
    nery
    -0.65
    cill
    -0.64
    soever
    -0.64
    ni
    -0.63
    POSITIVE LOGITS
     reel
    0.92
     highlights
    0.85
    ibilities
    0.80
    ibility
    0.79
    Marginal
    0.71
     warnings
    0.71
     milestones
    0.71
     highlighting
    0.70
    OWS
    0.70
    umenthal
    0.70
    Act Density 0.049%

    No Known Activations