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

    Neuronpedia

    INDEX
    Explanations

    words related to maintenance or record-keeping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NER
    -0.81
    mob
    -0.74
    sonian
    -0.69
    Merit
    -0.68
    nir
    -0.65
    hel
    -0.65
    ner
    -0.65
    �
    -0.65
    tf
    -0.64
    MAN
    -0.63
    POSITIVE LOGITS
     quiet
    0.73
    oulos
    0.72
     track
    0.71
     secret
    0.70
     meticulous
    0.70
     silent
    0.68
     tabs
    0.68
     busy
    0.67
     score
    0.65
     calm
    0.65
    Act Density 0.038%

    No Known Activations