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

    Neuronpedia

    INDEX
    Explanations

    the closing brackets and end symbols in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reſ
    -1.12
     myſelf
    -1.08
     transfieras
    -1.02
     ―――――
    -1.01
     autorytatywna
    -1.01
     Италијани
    -0.99
     Diſ
    -0.98
     Monfieur
    -0.97
     ſche
    -0.96
     itſelf
    -0.96
    POSITIVE LOGITS
    abstractmethod
    0.71
     
    0.66
     I
    0.62
    <eos>
    0.61
     The
    0.59
    ↵↵
    0.58
     A
    0.57
     (
    0.57
     /
    0.56
    ↵↵↵
    0.54
    Act Density 0.518%

    No Known Activations