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

    Neuronpedia

    INDEX
    Explanations

    news updates with times mentioned

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ograms
    -0.75
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    urat
    -0.67
    venge
    -0.65
    oeuv
    -0.64
     clad
    -0.63
    sers
    -0.62
    vec
    -0.60
     tubing
    -0.59
     roam
    -0.58
    POSITIVE LOGITS
    ]:
    0.99
    :]
    0.85
     Deadline
    0.82
     Adds
    0.80
    meier
    0.79
    !]
    0.77
    iday
    0.75
     redacted
    0.73
    PDATED
    0.73
     2015
    0.73
    Act Density 0.089%

    No Known Activations