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

    Neuronpedia

    INDEX
    Explanations

    written references to blank spaces

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blank" related to emptiness or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EH
    -0.78
    WAYS
    -0.76
    APS
    -0.75
    pora
    -0.75
    SHARE
    -0.73
    IVERS
    -0.72
    CVE
    -0.72
    Downloadha
    -0.72
    oral
    -0.70
    OA
    -0.70
    POSITIVE LOGITS
     blank
    1.18
     slate
    1.00
    ety
    0.94
     Blank
    0.92
    blank
    0.88
    eting
    0.82
     stares
    0.80
    etry
    0.79
    foundland
    0.73
    buster
    0.69
    Act Density 0.004%

    No Known Activations