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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal terms or positions, particularly related to investigations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal investigations and special teams or forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wid
    -0.69
    involved
    -0.66
     Split
    -0.66
    comings
    -0.63
    less
    -0.63
    cru
    -0.62
     Mehran
    -0.61
     Lov
    -0.60
    nen
    -0.59
    iour
    -0.59
    POSITIVE LOGITS
    Initialized
    0.82
    izabeth
    0.82
    phthal
    0.75
    utenant
    0.74
    Õ
    0.71
    hani
    0.70
    vation
    0.70
    asury
    0.69
    vity
    0.69
    viation
    0.69
    Act Density 0.163%

    No Known Activations