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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate existence or belief in entities and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aepernick
    -0.15
    pok
    -0.13
    ¼åIJĪ
    -0.13
    ÃŃn
    -0.12
    .rar
    -0.12
    ouch
    -0.12
    ìħĺ
    -0.12
    Ь
    -0.12
    ĵåIJį
    -0.12
    nar
    -0.12
    POSITIVE LOGITS
     exist
    1.12
     exists
    1.06
     existence
    0.96
     existed
    0.94
     Exist
    0.94
    exists
    0.90
    exist
    0.88
     Exists
    0.85
    Exist
    0.84
     existing
    0.84
    Act Density 0.301%

    No Known Activations