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

    Neuronpedia

    INDEX
    Explanations

    expressions related to numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     coté
    -0.71
     vainqueur
    -0.70
     shenan
    -0.69
     éto
    -0.68
     lapin
    -0.67
     unspeak
    -0.67
     désert
    -0.67
     delà
    -0.66
     levier
    -0.66
     phare
    -0.66
    POSITIVE LOGITS
     sappi
    0.67
     glance
    0.64
     vecin
    0.53
    vece
    0.53
     ridu
    0.53
     perif
    0.52
     ideolog
    0.51
     complic
    0.50
     democra
    0.50
     volete
    0.50
    Act Density 0.075%

    No Known Activations