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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to rules and structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     us
    -0.48
    itamos
    -0.45
    ряду
    -0.45
     ourselves
    -0.43
     antic
    -0.42
    Descriere
    -0.42
     consumers
    -0.41
     invas
    -0.41
    
    -0.41
     hosts
    -0.40
    POSITIVE LOGITS
     career
    1.19
    career
    1.08
     Career
    1.02
    Career
    0.97
     CAREER
    0.97
    CAREER
    0.91
     careers
    0.90
     carrière
    0.89
     Karriere
    0.83
     Careers
    0.82
    Act Density 0.922%

    No Known Activations