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

    Neuronpedia

    INDEX
    Explanations

    descriptions of crime events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vogli
    -0.83
     ecru
    -0.82
     Facile
    -0.80
     bandung
    -0.78
     swarovski
    -0.76
     Février
    -0.76
     credere
    -0.75
     dimenti
    -0.74
     tupperware
    -0.73
     cushi
    -0.72
    POSITIVE LOGITS
     suddenly
    0.52
     sudden
    0.51
     rushed
    0.50
     panic
    0.47
     yelling
    0.46
     rush
    0.46
     evacuated
    0.46
     immediately
    0.46
     seemed
    0.46
    ötzlich
    0.46
    Act Density 0.455%

    No Known Activations