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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of expansion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.34
     ―――――
    -1.21
     Jefus
    -1.18
     Eſ
    -1.17
     doubtnut
    -1.16
     Monfieur
    -1.15
     iſt
    -1.15
     Anſ
    -1.14
     Houſe
    -1.14
     Majefty
    -1.13
    POSITIVE LOGITS
     
    0.78
    ,
    0.73
    <strong>
    0.72
     are
    0.68
     say
    0.67
     can
    0.67
     The
    0.65
     ,
    0.64
     (
    0.63
    .
    0.61
    Act Density 0.142%

    No Known Activations