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

    Neuronpedia

    INDEX
    Explanations

    the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.73
     cauſe
    -0.73
     myſelf
    -0.72
     Monfieur
    -0.70
     leaſt
    -0.68
    principalTable
    -0.67
     purpoſe
    -0.67
     ſtate
    -0.64
     themſelves
    -0.63
     deſt
    -0.62
    POSITIVE LOGITS
    with
    1.52
     WITH
    1.43
     with
    1.41
    WITH
    1.38
     With
    1.38
     avec
    1.28
    With
    1.25
    Avec
    1.23
     Avec
    1.19
    avec
    1.14
    Act Density 0.366%

    No Known Activations