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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements and data related to chemical or biological assays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.93
    ########.
    -0.86
    IsMutable
    -0.80
    iſchen
    -0.77
     queſta
    -0.76
     dieſe
    -0.74
    <unused3>
    -0.73
    <unused23>
    -0.73
    [@BOS@]
    -0.73
    <pad>
    -0.73
    POSITIVE LOGITS
    ↵
    0.40
    ?
    0.36
    </h2>
    0.35
    </td>
    0.34
    ↵↵
    0.33
    :
    0.32
     Baumann
    0.31
     luces
    0.31
     natural
    0.30
     ninguno
    0.30
    Act Density 1.696%

    No Known Activations