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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement or legal terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the root word "polic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ò
    -0.79
    URA
    -0.76
    stood
    -0.73
    LV
    -0.72
    Hidden
    -0.72
    bite
    -0.71
    conom
    -0.69
    Xi
    -0.69
    Newsletter
    -0.67
    Hung
    -0.66
    POSITIVE LOGITS
    ity
    0.99
    chio
    0.94
    olic
    0.92
     acid
    0.89
     acids
    0.81
    ulty
    0.80
    itionally
    0.78
    ities
    0.78
    enza
    0.74
    ipop
    0.73
    Act Density 0.015%

    No Known Activations