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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -1.04
     purpoſe
    -1.01
     auroit
    -0.98
    Geplaatst
    -0.94
     houſe
    -0.92
     feroit
    -0.91
     Inscrivez
    -0.91
     pleaſure
    -0.89
     avoient
    -0.88
     myſelf
    -0.85
    POSITIVE LOGITS
     “
    0.73
    "])
    0.73
    "):
    0.71
     
    0.71
     saites
    0.70
    ัพท์
    0.65
     be
    0.64
    %")
    0.62
     an
    0.62
     major
    0.62
    Act Density 0.283%

    No Known Activations