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

    Neuronpedia

    INDEX
    Explanations

    terms associated with unexpected events and disruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     se
    -0.79
     la
    -0.52
    ContextHolder
    -0.48
    DataMember
    -0.46
    Se
    -0.45
     ту
    -0.44
     Verfügung
    -0.43
    be
    -0.43
    谨
    -0.43
    有多
    -0.43
    POSITIVE LOGITS
     interrupted
    1.54
     unexpected
    1.52
     disruption
    1.51
     disruptions
    1.51
     disrupted
    1.48
     interruptions
    1.47
     disrupt
    1.45
     interruption
    1.42
     interrupts
    1.40
     interrupt
    1.39
    Act Density 0.078%

    No Known Activations