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

    Neuronpedia

    INDEX
    Explanations

    references to statistical averages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     correspond
    -0.33
     corresponde
    -0.29
    interopRequire
    -0.29
     corresponded
    -0.27
     frecuencia
    -0.25
     corresponden
    -0.25
     resultan
    -0.25
    apatan
    -0.25
     Autorisations
    -0.25
     ü
    -0.24
    POSITIVE LOGITS
    parsedMessage
    0.77
     recent
    0.71
    recent
    0.69
     iprot
    0.66
    hanced
    0.63
    цездатний
    0.62
    Majestic
    0.62
     nahilalakip
    0.62
    __(/*!
    0.62
    sampling
    0.61
    Act Density 0.304%

    No Known Activations