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

    Neuronpedia

    INDEX
    Explanations

    expressions of well-being or positive feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.74
    RunWith
    -0.73
     المعيارى
    -0.72
     fhort
    -0.66
     massively
    -0.63
     fhew
    -0.62
    köz
    -0.61
    Зноскі
    -0.61
    wapV
    -0.61
     myſelf
    -0.60
    POSITIVE LOGITS
    Good
    1.47
     Good
    1.41
     good
    1.40
    good
    1.36
    GOOD
    1.36
     GOOD
    1.35
     bien
    1.02
     buen
    0.99
     buena
    0.90
     goodness
    0.90
    Act Density 0.241%

    No Known Activations