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

    Neuronpedia

    INDEX
    Explanations

    code segments related to function definitions and settings management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.94
    abestanden
    -0.77
    nologue
    -0.73
    DockStyle
    -0.72
     DMT
    -0.69
    RetentionPolicy
    -0.66
    twimg
    -0.63
    bootstrapcdn
    -0.63
     Giordano
    -0.61
    Хьажоргаш
    -0.61
    POSITIVE LOGITS
     COLD
    0.55
     alá
    0.55
    assertIn
    0.53
    couts
    0.52
     behalf
    0.52
     Cold
    0.52
     accountant
    0.52
                                   
    0.52
     Pristupljeno
    0.51
     Accountant
    0.51
    Act Density 0.129%

    No Known Activations