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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating proof or evidence of various outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reme
    -0.16
    inish
    -0.15
    rena
    -0.15
    ropolis
    -0.15
    DNA
    -0.15
     Dane
    -0.14
    omo
    -0.14
    cks
    -0.14
     Romeo
    -0.14
    osaurs
    -0.14
    POSITIVE LOGITS
    ource
    0.16
     bý
    0.16
    agma
    0.16
    erra
    0.15
    SSION
    0.15
     kaynaģı
    0.15
    λÏį
    0.14
    íĿ¥
    0.14
    UV
    0.14
    forth
    0.14
    Act Density 0.025%

    No Known Activations