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

    Neuronpedia

    INDEX
    Explanations

    numeric identifiers or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.08
     myſelf
    -1.06
     ―――――
    -1.04
    neſs
    -0.93
     ་་
    -0.93
    wiſe
    -0.91
    leſs
    -0.91
     Diſ
    -0.91
    ſelf
    -0.90
     pleaſure
    -0.89
    POSITIVE LOGITS
     Q
    2.15
    Q
    2.02
     q
    1.57
    q
    1.48
    ｑ
    1.15
    Qs
    1.05
    Ｑ
    1.01
     Qantas
    0.92
    qtype
    0.89
    Quercus
    0.88
    Act Density 0.140%

    No Known Activations