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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to crime and its analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dech
    -0.17
    ERE
    -0.16
    gom
    -0.15
    gren
    -0.15
    -mf
    -0.15
    fid
    -0.15
     gren
    -0.14
     comprom
    -0.14
    antro
    -0.14
     mines
    -0.13
    POSITIVE LOGITS
     crime
    0.35
     criminal
    0.34
     Crime
    0.32
     Criminal
    0.32
    Crime
    0.29
    crime
    0.29
     sentencing
    0.29
    criminal
    0.28
     cr
    0.28
    åĪij
    0.27
    Act Density 0.119%

    No Known Activations