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

    Neuronpedia

    INDEX
    Explanations

    references to academic achievements and educational pursuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aliz
    -0.17
    Instruction
    -0.15
    NP
    -0.14
     instruction
    -0.14
     rumor
    -0.14
     Instruction
    -0.14
     rumors
    -0.14
    ÑĢел
    -0.14
     rumored
    -0.14
     saber
    -0.14
    POSITIVE LOGITS
    Fd
    0.25
    sand
    0.21
     Foundation
    0.21
     sandwich
    0.21
     foundation
    0.21
    Pg
    0.21
     Sandwich
    0.20
     hon
    0.20
     Brun
    0.19
     Pg
    0.19
    Act Density 0.061%

    No Known Activations