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

    Neuronpedia

    INDEX
    Explanations

    questions involving the letter "Q" or references to queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neſs
    -0.79
     ―――――
    -0.78
    leſs
    -0.76
    ſhip
    -0.74
     myſelf
    -0.70
     ……………………
    -0.70
    wiſe
    -0.69
     itſelf
    -0.69
     ――――――――
    -0.69
    ………………………………
    -0.68
    POSITIVE LOGITS
     Q
    2.30
    Q
    2.13
     q
    1.70
    q
    1.52
    ｑ
    1.19
    Qs
    1.16
    Ｑ
    1.14
    iQ
    1.02
     Qantas
    0.99
    qtype
    0.99
    Act Density 0.116%

    No Known Activations