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

    Neuronpedia

    INDEX
    Explanations

    references to programming functions or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.93
    <eos>
    -0.92
    ↵↵
    -0.76
    </tr>
    -0.58
    [toxicity=0]
    -0.56
    <tr>
    -0.56
    ↵↵↵
    -0.54
     It
    -0.54
    ()]);
    -0.53
    -0.52
    POSITIVE LOGITS
    ThroughAttribute
    0.91
    脚注の使い方
    0.85
    Sucesor
    0.79
     autorytatywna
    0.78
    WithIOException
    0.76
    ManagedBean
    0.76
    HostException
    0.75
     surla
    0.74
     utafitiHapana
    0.74
     disambiguazione
    0.73
    Act Density 0.031%
    No Known Activations