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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data handling and sharing procedures

    oai_token-act-pair · gpt-3.5-turbo

    modal and auxiliary verbs indicating existence or state in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggle
    -0.84
     Raise
    -0.73
    inav
    -0.71
     externalToEVAOnly
    -0.70
    rek
    -0.70
    tackle
    -0.70
     congr
    -0.70
    ionics
    -0.70
    autions
    -0.69
     Tackle
    -0.68
    POSITIVE LOGITS
     stored
    1.26
     encrypted
    1.25
     archived
    1.22
     uploaded
    1.20
     scanned
    1.19
     leaked
    1.18
     retrieved
    1.17
     collected
    1.16
     retri
    1.16
     forwarded
    1.15
    Act Density 0.231%

    No Known Activations