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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "with."

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

    "with"

    np_acts-logits-general · gemini-2.0-flash

    with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.59
    URLException
    -0.56
     enfans
    -0.55
    ſelf
    -0.53
     purpoſe
    -0.52
    Jeografia
    -0.52
     fubject
    -0.51
     StatelessWidget
    -0.51
     religione
    -0.50
    ynchronously
    -0.49
    POSITIVE LOGITS
    with
    0.97
     WITH
    0.88
    WITH
    0.87
    With
    0.84
     With
    0.78
     Avec
    0.74
    dengan
    0.73
     אית
    0.68
    avec
    0.67
     avec
    0.66
    Act Density 0.463%

    No Known Activations