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

    Neuronpedia

    INDEX
    Explanations

    terms related to account verification processes and associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -0.93
     lenker
    -0.90
     queſta
    -0.89
    <unused41>
    -0.85
     ſche
    -0.85
    <unused23>
    -0.85
    <unused43>
    -0.84
    <unused47>
    -0.84
    <unused28>
    -0.84
    <pad>
    -0.84
    POSITIVE LOGITS
     St
    0.79
    ↵↵
    0.78
     to
    0.77
     I
    0.76
     A
    0.75
     G
    0.74
     Pro
    0.73
    ,
    0.73
     Re
    0.73
     P
    0.73
    Act Density 0.549%

    No Known Activations