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

    Neuronpedia

    INDEX
    Explanations

    rare or uncommon words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate rarity or frequency classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otom
    -0.80
    pora
    -0.80
    apo
    -0.74
    olulu
    -0.71
    aeper
    -0.71
    £ı
    -0.69
    owe
    -0.68
     retreat
    -0.66
    illation
    -0.66
    andering
    -0.65
    POSITIVE LOGITS
    ly
    0.86
    wealth
    0.81
     Beetle
    0.76
     Creature
    0.75
     Diseases
    0.72
     Uncommon
    0.72
     Common
    0.72
    Sense
    0.71
     Keys
    0.71
     Lisp
    0.71
    Act Density 0.026%

    No Known Activations