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

    Neuronpedia

    INDEX
    Explanations

    dates in specific formats

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gnition
    -0.59
     tupperware
    -0.56
    Naphthalene
    -0.53
     notori
    -0.52
     [''],
    -0.51
     hdi
    -0.51
     saites
    -0.51
     softshell
    -0.50
     argan
    -0.50
    tificial
    -0.50
    POSITIVE LOGITS
     eccellente
    0.52
     singola
    0.51
     esterna
    0.48
     knelt
    0.48
     sicura
    0.48
     Église
    0.48
     assolu
    0.47
     elettrico
    0.47
     essenziale
    0.46
     anteriore
    0.46
    Act Density 0.064%

    No Known Activations