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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal contexts, penal codes, criminal activities, and enforcement mechanisms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    youtu
    -0.23
     Outbreak
    -0.22
     Seym
    -0.21
    worth
    -0.21
     livest
    -0.21
    stones
    -0.20
    acular
    -0.20
    ktop
    -0.20
    timer
    -0.20
    blance
    -0.20
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.33
     penal
    0.31
    icum
    0.26
    ized
    0.25
    vertis
    0.25
    TAIN
    0.24
    essed
    0.24
    ity
    0.24
    ities
    0.23
    utions
    0.23
    Act Density 8.732%

    No Known Activations