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

    Neuronpedia

    INDEX
    Explanations

    words related to the political situation in some region

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or entities in news contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gling
    -0.82
     glim
    -0.79
    pins
    -0.73
    Ü
    -0.72
    ateurs
    -0.71
    livious
    -0.68
    ateur
    -0.68
    ensical
    -0.67
    anted
    -0.67
    manship
    -0.66
    POSITIVE LOGITS
    eta
    1.22
    emia
    0.87
    quez
    0.87
    ichi
    0.81
    fter
    0.78
    fters
    0.78
    zza
    0.78
    ilon
    0.77
     Rossi
    0.76
     Centauri
    0.76
    Act Density 0.008%

    No Known Activations