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

    Neuronpedia

    INDEX
    Explanations

    currency symbols or financial references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.96
    iſchen
    -0.93
     queſta
    -0.92
    expandindo
    -0.91
    niſſe
    -0.90
    parsedMessage
    -0.89
    ſelben
    -0.87
    aarrggbb
    -0.86
    iſche
    -0.85
     ProtoMessage
    -0.85
    POSITIVE LOGITS
     
    0.40
    1
    0.39
    <eos>
    0.37
    2
    0.37
    3
    0.37
    4
    0.35
    7
    0.34
    or
    0.34
    ↵↵
    0.34
    0
    0.33
    Act Density 1.377%

    No Known Activations