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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    themes related to newness or innovation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HC
    -0.60
    å¦
    -0.58
     Advertisement
    -0.57
    `.
    -0.56
    APTER
    -0.54
     Rew
    -0.54
    ãĤ¦ãĤ¹
    -0.54
    Magikarp
    -0.53
    yip
    -0.53
     Mub
    -0.52
    POSITIVE LOGITS
     (),
    0.71
    ,[
    0.68
    ?),
    0.62
    })
    0.59
    rium
    0.58
     ())
    0.57
    ?,
    0.57
    iatus
    0.57
    ),
    0.57
    —"
    0.56
    Act Density 1.582%

    No Known Activations