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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quick visual assessment or perception

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "glance" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.78
    Christmas
    -0.69
    contract
    -0.69
    icer
    -0.68
    erto
    -0.68
    Chance
    -0.67
    estern
    -0.66
    trump
    -0.65
    Merit
    -0.65
    unic
    -0.65
    POSITIVE LOGITS
     glance
    1.28
     glances
    0.88
     afar
    0.88
    seeing
    0.85
     Takeru
    0.85
     IMAGES
    0.81
    finder
    0.79
     headlights
    0.76
     inquire
    0.75
    lessly
    0.72
    Act Density 0.027%

    No Known Activations