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

    Neuronpedia

    INDEX
    Explanations

    names of politicians and public figures

    oai_token-act-pair · gpt-3.5-turbo

    references to cycling events and athletes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Footnote
    -0.75
    âĹ¼
    -0.74
     ().
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    ãĤ¹
    -0.64
    Cla
    -0.64
    fortunately
    -0.63
     Lifetime
    -0.63
     Mechanical
    -0.62
    å®
    -0.62
    POSITIVE LOGITS
     slams
    1.24
     approves
    1.21
     warns
    1.18
     defends
    1.15
     reacts
    1.13
     urges
    1.13
     announces
    1.12
     shuts
    1.11
     praises
    1.10
     condemns
    1.09
    Act Density 0.533%

    No Known Activations