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

    Neuronpedia

    INDEX
    Explanations

    oscillation phenomena in the data

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     mutations
    -0.94
     ujednoznacz
    -0.84
     Mutations
    -0.72
    WaitGroup
    -0.68
     autorytatywna
    -0.67
     telt
    -0.65
    mutations
    -0.64
    enderror
    -0.64
    دانشنامهٔ
    -0.63
     violations
    -0.62
    POSITIVE LOGITS
     mutation
    1.17
     oscillation
    0.98
     Mutation
    0.94
    Mutation
    0.72
    mutation
    0.68
     fluctuation
    0.62
     Bourgoin
    0.56
     vibration
    0.53
    писание
    0.50
     hernia
    0.50
    Act Density 0.006%

    No Known Activations