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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.72
    terly
    -0.65
    MessageOf
    -0.52
    liptic
    -0.52
     sono
    -0.51
    iad
    -0.51
    SharedCtor
    -0.51
     are
    -0.50
    uning
    -0.49
     Re
    -0.49
    POSITIVE LOGITS
    évaluateur
    0.76
     дописавши
    0.67
    SBATCH
    0.67
     saites
    0.66
     AssemblyVersion
    0.62
    ujte
    0.62
    ftagPool
    0.59
    colha
    0.59
     Walkover
    0.58
    @[+][
    0.56
    Act Density 0.099%

    No Known Activations