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

    Neuronpedia

    INDEX
    Explanations

    phrases and references related to recent events or newly introduced concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suaminya
    -0.83
    berdayakan
    -0.83
     estekak
    -0.80
     Infór
    -0.78
    antaranya
    -0.77
     Bewußt
    -0.76
     auroit
    -0.75
     desmotivaciones
    -0.75
     pimpinan
    -0.75
     demonios
    -0.74
    POSITIVE LOGITS
     using
    0.86
     recently
    0.79
     Recently
    0.72
     ser
    0.66
     copper
    0.66
     fra
    0.65
    using
    0.65
     master
    0.63
     ud
    0.63
     ut
    0.62
    Act Density 0.418%

    No Known Activations