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

    Neuronpedia

    INDEX
    Explanations

    instances of disbelief or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avo
    -0.07
     Instances
    -0.07
    enberg
    -0.06
    edly
    -0.06
    adera
    -0.06
     bill
    -0.06
    emet
    -0.06
     likely
    -0.06
    678
    -0.06
    ACS
    -0.06
    POSITIVE LOGITS
     existence
    0.12
     exist
    0.12
     exists
    0.11
     Exist
    0.10
     existed
    0.09
     Exists
    0.09
    åŃĺåľ¨
    0.09
    existence
    0.09
     existe
    0.09
    Exist
    0.08
    Act Density 0.010%

    No Known Activations