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

    Neuronpedia

    INDEX
    Explanations

    references to group identities and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.77
    脚注の使い方
    -0.66
     occaf
    -0.65
    TagMode
    -0.64
     ſche
    -0.62
     cime
    -0.60
     purpoſe
    -0.60
     nutella
    -0.60
    Демографія
    -0.60
     shutil
    -0.60
    POSITIVE LOGITS
     spalle
    0.47
     namanya
    0.40
     árvore
    0.38
     hablado
    0.37
     his
    0.37
     loob
    0.35
    mişti
    0.34
     rocas
    0.33
    colns
    0.33
    ljiv
    0.33
    Act Density 1.242%

    No Known Activations