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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.77
    LESS
    -0.65
    PDATE
    -0.64
    ©¶æ
    -0.63
    manship
    -0.62
    CVE
    -0.60
     tenant
    -0.60
    pport
    -0.59
    Animation
    -0.59
    ummies
    -0.59
    POSITIVE LOGITS
     threshold
    1.03
     river
    0.94
     creek
    0.89
     boundaries
    0.88
     border
    0.87
     borders
    0.83
     aisle
    0.81
    estone
    0.79
     bounds
    0.79
     boundary
    0.76
    Act Density 0.073%

    No Known Activations