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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases related to the concept of invisibility

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of invisibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    req
    -0.74
    xit
    -0.74
    olitan
    -0.72
    owder
    -0.72
    andals
    -0.72
    uden
    -0.70
    avanaugh
    -0.70
    iffs
    -0.69
    rim
    -0.69
    Interstitial
    -0.68
    POSITIVE LOGITS
     invisible
    1.03
     invis
    0.99
     volcano
    0.88
    abled
    0.79
     Invisible
    0.78
     phantom
    0.78
     unseen
    0.77
     invincible
    0.73
     disco
    0.73
    ibility
    0.73
    Act Density 0.011%

    No Known Activations