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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating association or connection with other entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.63
     purpoſe
    -0.57
    ſelf
    -0.55
     Monfieur
    -0.55
     leſs
    -0.54
     reaſon
    -0.53
     lefs
    -0.53
    ſelves
    -0.51
     beſt
    -0.51
     fubject
    -0.51
    POSITIVE LOGITS
     plus
    0.93
     ditambah
    0.80
    plus
    0.80
    makeText
    0.80
     Plus
    0.80
     accompanying
    0.78
     accompagné
    0.76
     accompanied
    0.76
     плюс
    0.73
     +
    0.73
    Act Density 0.265%

    No Known Activations