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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer software terms and technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "viv" or variations associated with life or vitality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    --------------------------------------------------------
    -0.87
    STER
    -0.77
     secrecy
    -0.70
    ————
    -0.68
    WHERE
    -0.64
     screw
    -0.62
     comma
    -0.62
     frivolous
    -0.62
    QU
    -0.60
     overpower
    -0.60
    POSITIVE LOGITS
    iew
    1.11
    iv
    1.09
    iral
    1.05
    irus
    0.99
    olution
    0.99
    isible
    0.98
    isions
    0.96
    iva
    0.95
    iera
    0.93
    itri
    0.93
    Act Density 0.014%

    No Known Activations