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

    Neuronpedia

    INDEX
    Explanations

    references to recent studies, reports, and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eventually
    -0.73
     later
    -0.67
    eventually
    -0.63
     currently
    -0.62
     today
    -0.61
     einst
    -0.61
     derzeit
    -0.60
     nantinya
    -0.59
     später
    -0.58
     Eventually
    -0.57
    POSITIVE LOGITS
     developments
    0.84
     additions
    0.82
     addition
    0.76
     discoveries
    0.71
     spate
    0.70
     Developments
    0.69
     happenings
    0.68
     arrivals
    0.64
     innovations
    0.63
     Additions
    0.63
    Act Density 0.208%

    No Known Activations