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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "break" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eid
    -0.18
    BER
    -0.17
    anges
    -0.16
    jar
    -0.16
    irth
    -0.15
    aut
    -0.15
    bers
    -0.15
    ói
    -0.15
     Ant
    -0.14
    imos
    -0.14
    POSITIVE LOGITS
    away
    0.31
    fast
    0.30
    neck
    0.27
    FAST
    0.26
    through
    0.26
    aways
    0.25
     ranks
    0.22
    bulk
    0.22
    Away
    0.21
    -even
    0.21
    Act Density 0.014%

    No Known Activations