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

    Neuronpedia

    INDEX
    Explanations

    phrases related to analysis and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entre
    -0.45
     mil
    -0.45
    miert
    -0.43
    pett
    -0.41
    <eos>
    -0.41
    oki
    -0.41
    atos
    -0.41
     
    -0.40
    atus
    -0.40
     ($
    -0.40
    POSITIVE LOGITS
     Anſ
    0.77
     AssemblyCompany
    0.74
    tagHelperRunner
    0.72
    antity
    0.69
     himſelf
    0.67
    abstractmethod
    0.67
     referenties
    0.65
     ſind
    0.65
     Monfieur
    0.64
     ioutil
    0.64
    Act Density 0.291%

    No Known Activations