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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and self-expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iç
    -0.29
     hjelp
    -0.28
     menengah
    -0.26
     bezpośred
    -0.25
     trozos
    -0.25
    räck
    -0.25
     cristales
    -0.24
     dítě
    -0.24
     umě
    -0.24
     sayesinde
    -0.23
    POSITIVE LOGITS
    tvguidetime
    0.93
     queſta
    0.93
    
    0.92
    quelize
    0.92
     zwiſchen
    0.90
    MENAFN
    0.86
     imagui
    0.84
    脚注の使い方
    0.83
    <unused16>
    0.82
    <unused52>
    0.82
    Act Density 0.165%

    No Known Activations