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

    Neuronpedia

    INDEX
    Explanations

    words related to proposals and suggested plans

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

    "Proposed" or "proposal"

    np_acts-logits-general · gemini-2.0-flash

    proposed explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lus
    -0.57
    طق
    -0.56
    ج
    -0.56
     kend
    -0.54
    asha
    -0.53
    in
    -0.52
    +
    -0.52
     Fortun
    -0.51
     Kor
    -0.51
    amina
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    1.36
     Proposals
    1.12
     proposals
    1.08
    Proposals
    1.02
     Proposal
    1.01
    POSAL
    0.99
    proposals
    0.99
     Baillargeon
    0.91
    PROPOSED
    0.87
    Proposal
    0.87
    Act Density 0.128%

    No Known Activations