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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" and related pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esterno
    -0.49
     esterna
    -0.47
     extérieure
    -0.43
     isOpen
    -0.42
    isOpen
    -0.41
     externi
    -0.39
    TypeEnum
    -0.39
    upné
    -0.39
     spirituale
    -0.38
    isempty
    -0.38
    POSITIVE LOGITS
     that
    0.96
    that
    0.91
    THAT
    0.90
     THAT
    0.88
    That
    0.86
     That
    0.85
     que
    0.76
     που
    0.75
     tht
    0.71
     ότι
    0.71
    Act Density 0.875%

    No Known Activations