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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting the reader to check out something, such as videos or articles

    oai_token-act-pair · gpt-3.5-turbo

    calls to action, particularly those encouraging the reader to "check out" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lishes
    -0.77
     suscept
    -0.69
    ãĥĨãĤ£
    -0.69
    minist
    -0.64
    EStreamFrame
    -0.63
    âĹ¼
    -0.61
    cffffcc
    -0.60
     mathemat
    -0.58
    ulton
    -0.57
    LOD
    -0.57
    POSITIVE LOGITS
    mate
    1.09
    boxes
    0.98
    lists
    0.93
    list
    0.89
    out
    0.89
    ups
    0.88
     out
    0.88
    outs
    0.85
    ers
    0.84
    points
    0.81
    Act Density 0.022%

    No Known Activations