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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social sciences and their empirical validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĵãģ©
    -0.14
    883
    -0.14
    ming
    -0.14
     neat
    -0.14
     lots
    -0.13
    let
    -0.13
     flexGrow
    -0.13
    azu
    -0.13
     decreased
    -0.13
     trick
    -0.13
    POSITIVE LOGITS
    TRS
    0.16
    amus
    0.15
     escorte
    0.15
    .nt
    0.15
    Ñıж
    0.15
    ignon
    0.14
    reative
    0.14
     Teil
    0.14
    aux
    0.14
     quantum
    0.14
    Act Density 0.005%

    No Known Activations