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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles containing a combination of letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific usernames or identifiers typically associated with social media accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrut
    -0.85
    conservancy
    -0.74
    ancies
    -0.71
    etheless
    -0.69
     mathemat
    -0.65
     nodd
    -0.64
     arrang
    -0.60
     differe
    -0.60
     withd
    -0.59
     suits
    -0.59
    POSITIVE LOGITS
     —
    1.11
    Jr
    0.89
    q
    0.87
     pic
    0.85
    X
    0.83
    Q
    0.77
    pic
    0.77
    8
    0.73
    &
    0.73
    E
    0.72
    Act Density 0.029%

    No Known Activations