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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.77
    ponses
    -0.75
    oredCriteria
    -0.72
     tartalomajánló
    -0.72
     EconPapers
    -0.71
    NewUrlParser
    -0.71
     myſelf
    -0.71
     Monfieur
    -0.70
    contentLoaded
    -0.69
    دانشنامهٔ
    -0.68
    POSITIVE LOGITS
     realize
    0.74
     realized
    0.69
     realizes
    0.68
     knew
    0.65
     realizing
    0.64
     knowing
    0.64
     realise
    0.63
    IBarButtonItem
    0.59
     realised
    0.58
     realises
    0.58
    Act Density 0.215%

    No Known Activations