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

    Neuronpedia

    INDEX
    Explanations

    indicators of significant events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -1.05
    .
    -0.84
    :
    -0.78
     –
    -0.73
     D
    -0.72
     S
    -0.71
    ;
    -0.71
     der
    -0.71
     A
    -0.69
     In
    -0.68
    POSITIVE LOGITS
     Majefty
    1.46
     Efq
    1.42
     itſelf
    1.39
     Houſe
    1.36
     doubtnut
    1.30
     Anſ
    1.25
     Reſ
    1.24
     Jefus
    1.24
     Monfieur
    1.21
     Diſ
    1.19
    Act Density 0.334%

    No Known Activations