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

    Neuronpedia

    INDEX
    Explanations

    locations and activities in a community or social setting

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ?".
    -0.67
     outwe
    -0.61
    âĢ¦"
    -0.58
    ··
    -0.55
    ?",
    -0.54
     ..."
    -0.53
     [...]
    -0.52
    </
    -0.52
     [âĢ¦]
    -0.52
     ourselves
    -0.52
    POSITIVE LOGITS
    itone
    0.65
    ansky
    0.58
    ãĤ´
    0.57
    ãĥĥãĤ¯
    0.56
    raf
    0.55
    veland
    0.55
    athered
    0.53
     himself
    0.52
     cameo
    0.51
     autobi
    0.51
    Act Density 13.183%

    No Known Activations