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

    Neuronpedia

    INDEX
    Explanations

    words related to credibility and invisibility

    oai_token-act-pair · gpt-3.5-turbo

    variations of the concept of "ability" or "capability."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.81
    battle
    -0.72
    ighth
    -0.68
    alogue
    -0.67
    ACH
    -0.65
    ãģį
    -0.65
    birth
    -0.63
    attacks
    -0.62
    Franc
    -0.62
    ghazi
    -0.61
    POSITIVE LOGITS
    ibility
    1.63
    ibilities
    1.25
    ibly
    1.09
    xtap
    0.92
    ible
    0.89
    IBLE
    0.88
    osate
    0.85
    ibles
    0.83
    ibl
    0.81
    ulnerability
    0.77
    Act Density 0.018%

    No Known Activations