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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "usual" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.53
     betweenstory
    -0.52
     gepubliceerd
    -0.51
     препратки
    -0.47
    basicConfig
    -0.45
     مشين
    -0.45
    hyrchwyd
    -0.44
    meisterschaften
    -0.43
    Demografie
    -0.43
     referenties
    -0.42
    POSITIVE LOGITS
     usual
    0.88
    usual
    0.87
    Usual
    0.85
     Usual
    0.84
     Usually
    0.55
    Usually
    0.53
     الرياضيه
    0.48
     usually
    0.46
    usually
    0.44
    UAL
    0.44
    Act Density 0.149%

    No Known Activations