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

    Neuronpedia

    INDEX
    Explanations

    negative sign indicators or formatting elements in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.94
     myſelf
    -1.90
     Efq
    -1.75
    ^(@)
    -1.70
     Forumite
    -1.64
     $_"
    -1.63
     Monfieur
    -1.62
    ſelves
    -1.62
     Jefus
    -1.61
     himſelf
    -1.60
    POSITIVE LOGITS
    (
    1.18
    _
    1.10
    ,
    1.08
    1.04
    -
    1.03
    /
    1.01
    ↵
    0.98
    .
    0.97
    :
    0.92
     (
    0.92
    Act Density 0.304%
    No Known Activations