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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "break" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eid
    -0.16
    amet
    -0.15
    opoulos
    -0.15
    phy
    -0.15
    irth
    -0.15
    دÙĪ
    -0.15
    aura
    -0.15
    ikan
    -0.14
    imos
    -0.14
    rr
    -0.14
    POSITIVE LOGITS
    fast
    0.36
    age
    0.34
    away
    0.33
    neck
    0.32
    water
    0.28
    FAST
    0.28
    ages
    0.27
    dance
    0.25
    through
    0.24
    aways
    0.24
    Act Density 0.040%

    No Known Activations