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

    Neuronpedia

    INDEX
    Explanations

    single characters that look like they are part of a special character or code sequence

    oai_token-act-pair · gpt-3.5-turbo

    the letter “L” in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.51
     vulner
    -0.51
     exha
    -0.48
     carbohyd
    -0.47
     sacrific
    -0.47
     hemor
    -0.47
     Seym
    -0.46
     circulation
    -0.45
     partnerships
    -0.45
     misunder
    -0.45
    POSITIVE LOGITS
    ï¸ı
    1.00
    ï¸
    0.78
    Balt
    0.63
    ··
    0.61
    ¯
    0.61
    Stra
    0.60
    âĶĢâĶĢâĶĢâĶĢ
    0.60
    İ
    0.60
    âĶĢâĶĢ
    0.58
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.57
    Act Density 0.568%

    No Known Activations