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

    Neuronpedia

    INDEX
    Explanations

    references to promises, commitments, and agreements, particularly in the context of keeping or breaking them

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

    pledges or guarantees

    np_acts-logits-general · gemini-2.0-flash

    promise or guarantee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.60
     Italijanski
    -0.59
    RenderAtEndOf
    -0.54
    AndEndTag
    -0.53
    Reuse
    -0.50
     percolation
    -0.48
     MainAxisSize
    -0.48
    ilación
    -0.47
    isher
    -0.47
    tachment
    -0.46
    POSITIVE LOGITS
     promise
    3.21
     promises
    2.83
     promised
    2.65
    promise
    2.64
     Promise
    2.56
     pledge
    2.44
    Promise
    2.43
     Promises
    2.32
    promises
    2.26
     pledges
    2.22
    Act Density 0.449%

    No Known Activations