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

    Neuronpedia

    INDEX
    Explanations

    words related to accusations and allegations in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utnik
    -0.65
     Shreve
    -0.64
     home
    -0.60
    marvin
    -0.60
     hjem
    -0.59
     Nutt
    -0.59
     Gw
    -0.56
     dandy
    -0.55
     unim
    -0.55
     roti
    -0.55
    POSITIVE LOGITS
     alleges
    1.07
     accuses
    1.06
     accuse
    1.05
     allege
    1.01
     allegations
    1.00
     accusations
    0.98
     accusing
    0.97
    Alleg
    0.91
     allegation
    0.91
     alleging
    0.91
    Act Density 0.141%

    No Known Activations