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

    Neuronpedia

    INDEX
    Explanations

    phrases related to information technology and data management

    oai_token-act-pair · gpt-3.5-turbo

    references to services and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.94
    terday
    -0.76
     destro
    -0.75
    hene
    -0.71
    atron
    -0.67
    ury
    -0.67
    tsky
    -0.66
    opoulos
    -0.66
     Strongh
    -0.64
    etheless
    -0.64
    POSITIVE LOGITS
    ========
    0.97
    ccording
    0.93
    ============
    0.91
    ³³³³³³³³³³³³³³³³
    0.83
    ---------
    0.81
    --------------------
    0.76
    ................................
    0.74
    Spoiler
    0.73
    ================
    0.72
    Language
    0.71
    Act Density 0.197%

    No Known Activations