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

    Neuronpedia

    INDEX
    Explanations

    mentions of missing persons and related circumstances

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    erenn
    -0.64
     renaissance
    -0.64
    ggles
    -0.62
    ateur
    -0.61
     versatility
    -0.59
     fascinating
    -0.59
     fasc
    -0.58
    iple
    -0.58
    reprene
    -0.57
     nostalgia
    -0.57
    POSITIVE LOGITS
    .''.
    1.07
    )).
    0.98
     thereto
    0.96
     thereof
    0.96
    .[
    0.94
    ]).
    0.91
     beforehand
    0.87
    usercontent
    0.86
     attRot
    0.82
     theirs
    0.81
    Act Density 1.203%

    No Known Activations