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

    Neuronpedia

    INDEX
    Explanations

    phrases related to protection and security

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    jet
    -0.67
    quartered
    -0.67
    ãĥ£
    -0.65
    LIN
    -0.64
    VP
    -0.62
    LINE
    -0.61
    gom
    -0.60
    hall
    -0.59
    quart
    -0.58
     vinegar
    -0.57
    POSITIVE LOGITS
    ively
    1.11
    iveness
    0.94
    ously
    0.91
    atively
    0.91
    orate
    0.90
    folios
    0.83
     against
    0.81
    ences
    0.76
     protecting
    0.76
    amental
    0.74
    Act Density 11.283%

    No Known Activations