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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and stories

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     mathemat
    -1.02
     taxp
    -0.83
     scram
    -0.82
     jog
    -0.81
     filib
    -0.80
     sacrific
    -0.79
     carbohyd
    -0.79
     accomp
    -0.79
     Jinn
    -0.76
     Commons
    -0.76
    POSITIVE LOGITS
    ï¸ı
    1.10
    tre
    1.07
    ï¸
    1.04
    ional
    1.03
    eal
    1.03
    tu
    1.01
    İ
    1.00
    ski
    1.00
    âĶĢâĶĢ
    0.99
    vest
    0.98
    Act Density 1.104%

    No Known Activations