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

    Neuronpedia

    INDEX
    Explanations

    words related to earning and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ides
    -0.15
    ape
    -0.14
    wire
    -0.14
    ase
    -0.14
    eldom
    -0.14
     readonly
    -0.14
     Dav
    -0.14
     crackers
    -0.14
    rael
    -0.14
    al
    -0.13
    POSITIVE LOGITS
     earn
    0.17
    égor
    0.17
    enance
    0.16
    ORITY
    0.16
     dela
    0.15
    pike
    0.15
    edList
    0.15
     earned
    0.15
     Earn
    0.15
    ÑĢаб
    0.15
    Act Density 0.021%

    No Known Activations