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

    Neuronpedia

    INDEX
    Explanations

    occurrences of conjunctions and numerical values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.74
     ſmall
    -0.70
     doubtnut
    -0.70
    Personensuche
    -0.69
     myſelf
    -0.69
     raiſ
    -0.69
     ujednoznacz
    -0.68
     pouvoit
    -0.66
     typelib
    -0.65
     houſe
    -0.65
    POSITIVE LOGITS
    va
    0.53
    complexContent
    0.50
     dAtA
    0.49
     MediaQuery
    0.48
     while
    0.48
    pop
    0.47
     mentre
    0.47
    ait
    0.46
      
    0.45
     plus
    0.45
    Act Density 0.684%

    No Known Activations