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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "made."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Made" followed by "from" or "of"

    np_acts-logits-general · gemini-2.0-flash

    made from or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.99
     Efq
    -0.98
     purpoſe
    -0.96
     myſelf
    -0.95
     Monfieur
    -0.92
     pleaſure
    -0.91
     raiſ
    -0.91
     houſe
    -0.89
     themſelves
    -0.89
     uſed
    -0.89
    POSITIVE LOGITS
     possible
    0.76
    possible
    0.65
     Possible
    0.63
     mogelijk
    0.62
     posible
    0.61
     ​​
    0.59
     POSSIBLE
    0.58
    Possible
    0.57
     möjligt
    0.57
     möglich
    0.52
    Act Density 0.074%

    No Known Activations