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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "spoil" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    spoil, spoilt, ruined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fahrzeug
    -0.52
     createContext
    -0.48
    dataclass
    -0.47
    -0.47
     Jacobson
    -0.46
     vectorielle
    -0.45
     CommonModule
    -0.44
     Ibid
    -0.44
     FetchType
    -0.43
     DbContext
    -0.43
    POSITIVE LOGITS
     spoil
    1.96
     spoiling
    1.74
     spoiled
    1.73
     spoils
    1.56
     spoilt
    1.48
    spo
    1.42
     Spo
    1.20
     spoiler
    1.16
    Spo
    1.13
    spoiler
    1.06
    Act Density 0.004%

    No Known Activations