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

    Neuronpedia

    INDEX
    Explanations

    phrases related to media and premieres

    oai_token-act-pair · gpt-3.5-turbo

    mentions of media organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dimensional
    -0.79
    sided
    -0.74
    holes
    -0.71
    chev
    -0.70
    ilk
    -0.69
    igel
    -0.68
    lake
    -0.68
    annis
    -0.68
    vine
    -0.68
    ills
    -0.68
    POSITIVE LOGITS
     Naw
    0.78
     ãĤµ
    0.75
    bledon
    0.74
     Kyr
    0.73
     Fug
    0.72
    ãĥŁ
    0.72
     Bow
    0.72
     Alz
    0.68
    ãĥĬ
    0.68
    Downloadha
    0.68
    Act Density 0.000%

    No Known Activations