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

    Neuronpedia

    INDEX
    Explanations

    instances of deception or pretense in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pamięci
    -0.41
     juicio
    -0.40
     boxeo
    -0.37
     venganza
    -0.37
     neón
    -0.37
     zimowe
    -0.37
     computadoras
    -0.36
     dignidad
    -0.35
     srdce
    -0.35
     tiroirs
    -0.35
    POSITIVE LOGITS
     pretended
    0.67
     HasFactory
    0.66
     AssemblyTitle
    0.66
     estekak
    0.65
     pretend
    0.64
     pseud
    0.58
     pretending
    0.58
    pret
    0.58
     pretends
    0.57
    ########.
    0.57
    Act Density 0.421%

    No Known Activations