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

    Neuronpedia

    INDEX
    Explanations

    short phrases or clauses beginning with "there is" or "there are"

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    farious
    -0.70
    arthy
    -0.63
     destro
    -0.62
    iterranean
    -0.59
    è¦ļéĨĴ
    -0.59
    ',"
    -0.58
    existent
    -0.58
    ],"
    -0.57
    ocobo
    -0.57
    "—
    -0.56
    POSITIVE LOGITS
    cknowled
    0.59
     largeDownload
    0.53
     Leader
    0.49
    oret
    0.49
     Remastered
    0.49
     Warp
    0.48
    SCP
    0.48
     Orbit
    0.48
     Shot
    0.48
    resy
    0.47
    Act Density 0.441%

    No Known Activations