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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "mal" which typically relates to negative or abnormal conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chofe
    -0.93
     quæ
    -0.91
     itſelf
    -0.88
     raiſ
    -0.87
     tjän
    -0.86
     berätt
    -0.82
     ſta
    -0.82
     neceff
    -0.81
     ainfi
    -0.80
     fubject
    -0.80
    POSITIVE LOGITS
     Mal
    2.56
     mal
    2.51
    Mal
    2.49
    mal
    2.31
     MAL
    2.23
    MAL
    2.00
     Malone
    1.39
     Malt
    1.31
     Mala
    1.30
     Mald
    1.28
    Act Density 0.064%

    No Known Activations