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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associations in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -2.22
     myſelf
    -2.08
     itſelf
    -2.06
    ^(@)
    -1.92
     Theſe
    -1.89
     Jefus
    -1.89
    ſelf
    -1.83
     purpoſe
    -1.83
     pleaſure
    -1.82
     themſelves
    -1.80
    POSITIVE LOGITS
    8
    1.48
    6
    1.41
    7
    1.38
    ,
    1.22
    0
    1.22
    9
    1.21
    -
    1.14
    5
    1.09
     and
    1.05
    /
    1.04
    Act Density 0.834%

    No Known Activations