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

    Neuronpedia

    INDEX
    Explanations

    constructs related to collective experiences and general statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apon
    -0.17
     both
    -0.14
     Populate
    -0.14
     consist
    -0.13
    uforia
    -0.13
     pylint
    -0.13
    lan
    -0.13
    town
    -0.13
     each
    -0.13
     triumph
    -0.13
    POSITIVE LOGITS
     adds
    0.17
     happening
    0.17
     cul
    0.17
    iem
    0.16
     done
    0.16
     stuff
    0.16
    maal
    0.16
     adding
    0.16
     contributes
    0.15
     while
    0.15
    Act Density 0.073%

    No Known Activations