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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or purposes involving the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.77
     pleaſure
    -0.73
     löytyy
    -0.71
     Wrang
    -0.71
     againſt
    -0.71
     sauvages
    -0.70
    Touching
    -0.70
     poffible
    -0.69
     grecque
    -0.69
     assignable
    -0.69
    POSITIVE LOGITS
     be
    1.09
     have
    0.94
     become
    0.85
     go
    0.80
     do
    0.76
     could
    0.75
     come
    0.74
     actually
    0.73
     make
    0.73
     can
    0.72
    Act Density 0.168%

    No Known Activations