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

    Neuronpedia

    INDEX
    Explanations

    highlights or key points within a text

    oai_token-act-pair · gpt-3.5-turbo

    the term "Highlights" and related references to notable content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essee
    -0.94
    nery
    -0.93
    geoning
    -0.84
    atorial
    -0.80
    alysis
    -0.79
    oking
    -0.78
    ice
    -0.78
    esthes
    -0.76
    gas
    -0.76
    ggy
    -0.75
    POSITIVE LOGITS
     Highlights
    1.18
     Features
    0.86
     RELEASE
    0.78
     Hover
    0.78
     Battery
    0.77
    ailable
    0.76
    CRIP
    0.75
     GAME
    0.72
     Hamb
    0.72
    NF
    0.70
    Act Density 0.017%

    No Known Activations