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

    Neuronpedia

    INDEX
    Explanations

    phrases related to betrayal or deceit

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "travesty" in different contexts related to justice and legality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.79
     retention
    -0.72
    ensor
    -0.70
    hens
    -0.66
    enture
    -0.65
    lain
    -0.64
    etts
    -0.64
     equity
    -0.64
    sburgh
    -0.63
     Mellon
    -0.63
    POSITIVE LOGITS
    ppings
    1.11
    vest
    1.03
    pez
    0.98
    tty
    0.83
    ordinary
    0.81
    vert
    0.79
    ppers
    0.79
    pper
    0.79
    itors
    0.76
    azon
    0.75
    Act Density 0.021%

    No Known Activations