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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "break" and its variations, indicating a focus on significant changes or disruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irth
    -0.20
    raz
    -0.17
    uzzy
    -0.17
    idl
    -0.16
    IDL
    -0.16
     Schiff
    -0.16
    éĸ
    -0.15
    enderit
    -0.15
    .Reporting
    -0.14
    iffe
    -0.14
    POSITIVE LOGITS
     breaking
    0.32
     break
    0.30
     breaks
    0.29
    -breaking
    0.27
     Breaking
    0.27
     broke
    0.27
    Breaking
    0.27
    breaking
    0.26
    .break
    0.26
     Break
    0.25
    Act Density 0.038%

    No Known Activations