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

    Neuronpedia

    INDEX
    Explanations

    references to individual authors or researchers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beſ
    -0.76
     Theſe
    -0.75
     Diſ
    -0.74
     ſeveral
    -0.73
     Reſ
    -0.70
     ſee
    -0.70
     Anſ
    -0.68
     reaſon
    -0.68
     ―――――
    -0.68
        
    -0.65
    POSITIVE LOGITS
     J
    2.07
    J
    1.74
     j
    1.48
    j
    1.00
     L
    0.88
     M
    0.86
    Jj
    0.85
     تضيفلها
    0.84
    qJ
    0.84
    JJ
    0.84
    Act Density 0.079%

    No Known Activations