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

    Neuronpedia

    INDEX
    Explanations

    the past tense forms of the verbs "was" and "were."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.04
    PerformLayout
    -1.02
     ſever
    -0.98
    RegressionTest
    -0.96
     auffi
    -0.93
    -0.91
    Демографія
    -0.90
     незавершена
    -0.89
    ThroughAttribute
    -0.89
    httphttps
    -0.89
    POSITIVE LOGITS
     is
    1.63
     were
    1.32
     was
    1.18
     are
    1.13
     has
    0.83
     Is
    0.81
     isn
    0.76
     WERE
    0.76
    were
    0.74
     adalah
    0.72
    Act Density 0.430%

    No Known Activations