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

    Neuronpedia

    INDEX
    Explanations

    expressions of identity and existential questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weren
    -0.17
     suddenly
    -0.16
    imore
    -0.16
    uctor
    -0.15
    ;element
    -0.15
     wasn
    -0.15
     doesn
    -0.14
    inia
    -0.14
     didn
    -0.14
     declining
    -0.14
    POSITIVE LOGITS
     exist
    0.30
     exists
    0.29
     existing
    0.26
     existence
    0.26
     existed
    0.24
    exists
    0.24
    åŃĺåľ¨
    0.22
     Exists
    0.22
     operates
    0.22
     operate
    0.21
    Act Density 0.031%

    No Known Activations