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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal improvement and progressive change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opa
    -0.15
    adow
    -0.15
    edom
    -0.15
    æŀĿ
    -0.15
     lump
    -0.15
    flow
    -0.14
    ledge
    -0.14
    avers
    -0.14
    óz
    -0.13
     split
    -0.13
    POSITIVE LOGITS
     Contribution
    0.20
     contribution
    0.19
    203
    0.19
    -contrib
    0.17
     завÑĤÑĢа
    0.17
     contributing
    0.17
     tomorrow
    0.17
     contribute
    0.16
     Beitrag
    0.16
     contrib
    0.16
    Act Density 0.027%

    No Known Activations