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

    Neuronpedia

    INDEX
    Explanations

    hidden elements or secrets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nia
    -0.80
     Pwr
    -0.76
    rehens
    -0.75
    ctive
    -0.74
    odic
    -0.73
    urses
    -0.71
    alon
    -0.70
    Ħ¢
    -0.70
    umbn
    -0.70
    annis
    -0.70
    POSITIVE LOGITS
     gem
    0.97
     gems
    0.92
     behind
    0.88
     hidden
    0.88
     recess
    0.87
     treasures
    0.80
     treasure
    0.79
     meanings
    0.78
     Hidden
    0.78
     stash
    0.78
    Act Density 0.016%

    No Known Activations