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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events and scientific research findings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mschrijving
    -0.56
     Municipio
    -0.49
    Sqft
    -0.47
     Meksiko
    -0.47
     revisor
    -0.46
     intervi
    -0.45
     Interv
    -0.44
     Szer
    -0.44
    ఔ
    -0.44
     læng
    -0.44
    POSITIVE LOGITS
    principalColumn
    0.62
     anymore
    0.62
     ACTUALLY
    0.61
     necessarily
    0.59
    oughby
    0.58
     truly
    0.55
    heast
    0.53
     realy
    0.53
     actually
    0.52
     entirely
    0.52
    Act Density 0.379%

    No Known Activations