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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "mal" indicating malfeasance or misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.74
     Fargo
    -0.72
    æĸ¹
    -0.68
     Salvation
    -0.67
     Wide
    -0.66
     Defenders
    -0.66
    ALK
    -0.65
     Polk
    -0.64
     Decoder
    -0.64
     Hobby
    -0.63
    POSITIVE LOGITS
    ignant
    1.32
    practice
    1.18
    colm
    1.15
    absor
    1.15
    adies
    1.13
    formed
    1.10
    igned
    1.06
    igning
    1.02
    ady
    1.00
    adjusted
    1.00
    Act Density 0.005%

    No Known Activations