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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and accreditation

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with accreditation and safety standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.81
    geist
    -0.80
     hope
    -0.69
    hs
    -0.69
    çīĪ
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    vous
    -0.66
    wich
    -0.65
    PT
    -0.65
    uyomi
    -0.64
    POSITIVE LOGITS
    ommod
    1.22
    redited
    1.20
    enture
    1.12
    reditation
    1.09
    ompl
    1.06
    used
    1.01
    laim
    1.01
    identally
    0.99
    urate
    0.98
    imate
    0.96
    Act Density 0.005%

    No Known Activations