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

    Neuronpedia

    INDEX
    Explanations

    monetary values represented with a pound sign (£)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.66
     itſelf
    -1.57
    ſelf
    -1.47
     leaſt
    -1.46
     Jefus
    -1.44
     faſt
    -1.44
     $_"
    -1.43
     ―――――
    -1.43
     Efq
    -1.41
     Majefty
    -1.40
    POSITIVE LOGITS
     
    0.81
     _
    0.78
    <eos>
    0.74
    1
    0.70
    T
    0.68
    p
    0.65
     =
    0.65
    2
    0.64
    <
    0.64
     £
    0.64
    Act Density 0.132%

    No Known Activations