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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles of creative works

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     credere
    -0.70
     résine
    -0.66
     Cæsar
    -0.63
     emozioni
    -0.62
     centrifugal
    -0.61
     entret
    -0.60
     fhort
    -0.59
     Chine
    -0.58
    SqlServer
    -0.58
     Industrie
    -0.56
    POSITIVE LOGITS
     hipster
    0.74
    NPR
    0.71
     NPR
    0.70
    ulemon
    0.67
     granola
    0.66
     nonprofit
    0.65
     indie
    0.65
    loem
    0.65
     kayaks
    0.65
    bucha
    0.63
    Act Density 0.463%

    No Known Activations