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

    Neuronpedia

    INDEX
    Explanations

    references to articles and books worth reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.75
    Personensuche
    -0.73
    <bos>
    -0.69
    يكب
    -0.63
     RouterModule
    -0.62
    -0.60
    fromCharCode
    -0.60
    indd
    -0.59
     partielle
    -0.59
    ]=>
    -0.58
    POSITIVE LOGITS
     podcasts
    0.57
    onAttach
    0.50
     lectures
    0.48
     talks
    0.48
     essays
    0.47
     speeches
    0.46
     pry
    0.45
     documentaries
    0.45
    렵
    0.44
    famous
    0.44
    Act Density 0.270%

    No Known Activations