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

    Neuronpedia

    INDEX
    Explanations

    terms related to electrical charge and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تانيه
    -0.79
     للمعارف
    -0.75
     Orrell
    -0.75
    IANGLES
    -0.73
     bint
    -0.73
     שוליים
    -0.72
     BorderRadius
    -0.71
    .*")]
    -0.69
     Quij
    -0.68
     Мексичка
    -0.68
    POSITIVE LOGITS
     charges
    1.18
    CHARGE
    1.08
     charge
    1.07
    charges
    1.06
     Charges
    1.06
    charge
    1.05
     Charge
    1.00
    Charge
    0.97
    Charges
    0.97
     CHARGE
    0.93
    Act Density 0.074%

    No Known Activations