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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences where information is being provided or some form of credit is being given

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "courtesy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pton
    -0.86
    vals
    -0.82
    thin
    -0.80
    ggle
    -0.77
    atform
    -0.76
    ppy
    -0.73
    omsky
    -0.73
    ilipp
    -0.71
    akia
    -0.70
    clusions
    -0.70
    POSITIVE LOGITS
     courtesy
    1.27
    tesy
    1.18
    CLASSIFIED
    0.78
     Credit
    0.77
     Shutterstock
    0.76
     Courtesy
    0.76
    ilial
    0.75
     Thomson
    0.71
    ãĥ¼ãĥĨãĤ£
    0.70
    Credit
    0.69
    Act Density 0.005%

    No Known Activations