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

    Neuronpedia

    INDEX
    Explanations

    currency symbols followed by numbers, essentially identifying monetary values

    oai_token-act-pair · gpt-3.5-turbo

    financial figures or dollar amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tall
    -0.85
     Nare
    -0.74
     Gors
    -0.74
     Samson
    -0.74
    umbn
    -0.72
    £ı
    -0.71
     Sod
    -0.68
     Rud
    -0.66
     Samar
    -0.66
     Bend
    -0.65
    POSITIVE LOGITS
    $$$$
    0.97
    ©¶æ¥µ
    0.96
    HOME
    0.95
    $$
    0.94
    false
    0.91
    iris
    0.89
    tc
    0.85
    100
    0.85
    true
    0.82
    Self
    0.80
    Act Density 0.071%

    No Known Activations