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

    Neuronpedia

    INDEX
    Explanations

    terms related to data structure and persistence in software contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bal
    -0.46
    ,
    -0.44
     Rus
    -0.43
     polo
    -0.42
     logo
    -0.42
    -
    -0.41
     Mar
    -0.40
     char
    -0.39
     Pet
    -0.39
    _
    -0.39
    POSITIVE LOGITS
    majánló
    0.82
     يتيمه
    0.79
    worm
    0.79
     desmotivaciones
    0.78
    الحياه
    0.78
     queſta
    0.77
    <unused47>
    0.76
    <unused3>
    0.75
    [@BOS@]
    0.75
    <unused41>
    0.75
    Act Density 0.176%

    No Known Activations