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

    Neuronpedia

    INDEX
    Explanations

    German-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to Germany

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.87
    ctica
    -0.78
    lihood
    -0.76
    heed
    -0.74
    ording
    -0.72
    clus
    -0.70
    seeking
    -0.69
    ttes
    -0.69
    vae
    -0.68
    tis
    -0.68
    POSITIVE LOGITS
    wings
    1.19
     Chancellor
    1.09
     Bundesliga
    0.95
     shepherd
    0.91
    icus
    0.84
     chancellor
    0.84
     Aerospace
    0.83
    ic
    0.81
     Shepherd
    0.81
     Bundes
    0.81
    Act Density 0.031%

    No Known Activations