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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a condition of certainty or stipulation in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.35
     myſelf
    -1.26
     themſelves
    -1.12
     houſe
    -1.10
     Majefty
    -1.08
     $_"
    -1.08
    bibfield
    -1.06
     Jefus
    -1.04
     himſelf
    -1.03
     Monfieur
    -1.02
    POSITIVE LOGITS
    .
    0.72
    (
    0.69
    ↵↵
    0.66
    ,
    0.65
    ↵
    0.64
    -
    0.63
    “
    0.59
    <b>
    0.58
    T
    0.57
    _
    0.57
    Act Density 0.382%

    No Known Activations