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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms and words related to dependencies and foundations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to foundational ideas or principles that underpin systems and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WHERE
    -0.68
     footsteps
    -0.67
     Moves
    -0.65
    ppings
    -0.64
     unbeliev
    -0.63
    Times
    -0.63
     Roose
    -0.62
    imes
    -0.62
    veyard
    -0.62
     SPACE
    -0.62
    POSITIVE LOGITS
     depends
    0.83
     depend
    0.82
     depended
    0.81
     relies
    0.72
     principally
    0.71
    Ħ¢
    0.71
     base
    0.68
     indemn
    0.68
    ij士
    0.67
     derives
    0.67
    Act Density 0.090%

    No Known Activations