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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.58
    󠁢
    -0.58
    ImageContext
    -0.57
     betweenstory
    -0.51
     BoxDecoration
    -0.51
    archiviato
    -0.49
    ItemBackground
    -0.49
     joaat
    -0.48
    東西
    -0.48
    MLLoader
    -0.48
    POSITIVE LOGITS
     ability
    0.56
     own
    0.55
     their
    0.53
     his
    0.53
    their
    0.50
     suas
    0.48
    Their
    0.47
     THEIR
    0.47
     its
    0.46
     Their
    0.45
    Act Density 0.045%

    No Known Activations