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

    Neuronpedia

    INDEX
    Explanations

    Sentences concerning individuals' actions or statuses within specific organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Valiant
    -0.79
     Golem
    -0.77
     scattering
    -0.71
     Naz
    -0.70
     nod
    -0.69
     bye
    -0.69
     Paras
    -0.68
     scatter
    -0.66
     Sakuya
    -0.65
     Nam
    -0.65
    POSITIVE LOGITS
    £
    0.95
    ¹
    0.92
    âĢł
    0.91
    Į
    0.88
    ¢
    0.87
    ISIS
    0.87
    §
    0.84
    taboola
    0.83
    ı
    0.82
    Colorado
    0.81
    Act Density 0.501%

    No Known Activations