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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.63
    commod
    -0.57
     vectorielle
    -0.53
    strophic
    -0.52
    inigungs
    -0.51
     AssemblyTitle
    -0.50
     abz
    -0.50
    oporosis
    -0.49
    Бележки
    -0.49
    produkt
    -0.48
    POSITIVE LOGITS
     himself
    0.82
    His
    0.82
     He
    0.80
     His
    0.79
     his
    0.79
     Himself
    0.79
     him
    0.78
    He
    0.75
    彼は
    0.69
    She
    0.66
    Act Density 0.511%

    No Known Activations