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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "idx" and related references to indices or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused43>
    -0.83
    <unused79>
    -0.82
    <unused41>
    -0.82
     queſta
    -0.82
    <unused23>
    -0.82
    <unused8>
    -0.82
    <unused14>
    -0.82
    [@BOS@]
    -0.82
    <unused47>
    -0.82
    <unused3>
    -0.81
    POSITIVE LOGITS
     Storm
    0.49
     
    0.47
     Lam
    0.47
     multi
    0.46
     Electro
    0.45
    gn
    0.44
     Kra
    0.44
     Dre
    0.43
     con
    0.43
     www
    0.42
    Act Density 0.250%

    No Known Activations