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

    Neuronpedia

    INDEX
    Explanations

    text elements that indicate procedural or legal formalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fod
    -0.89
    — 
    -0.83
     Borja
    -0.77
    EndInit
    -0.75
     Bess
    -0.74
    Geplaatst
    -0.74
    annica
    -0.72
     Merritt
    -0.71
     nahilalakip
    -0.71
    Personensuche
    -0.71
    POSITIVE LOGITS
    ________________
    1.70
    ______________
    1.00
    ____________
    0.95
    _____________
    0.93
    _______
    0.91
    __________
    0.89
    _____
    0.89
    _______________
    0.86
     ____________
    0.84
    ______
    0.84
    Act Density 0.033%

    No Known Activations