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

    Neuronpedia

    INDEX
    Explanations

    evidence-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various aspects of evidence in criminal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategory
    -0.77
    orks
    -0.75
    awar
    -0.74
    yright
    -0.69
    lisher
    -0.68
    TOR
    -0.66
    Hop
    -0.66
     Wonderful
    -0.66
    pop
    -0.65
    idays
    -0.65
    POSITIVE LOGITS
     tampering
    1.03
     evidence
    0.94
    evidence
    0.91
    abilia
    0.90
    intel
    0.81
     Evidence
    0.80
     testifying
    0.77
    glass
    0.75
    uments
    0.73
     incrim
    0.73
    Act Density 0.036%

    No Known Activations