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

    Neuronpedia

    INDEX
    Explanations

    phrases related to platforms or establishments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    intent
    -0.89
    votes
    -0.81
    achu
    -0.80
    acid
    -0.71
    eston
    -0.70
    istar
    -0.70
    enery
    -0.69
    errors
    -0.68
    arten
    -0.68
     Oliv
    -0.67
    POSITIVE LOGITS
     catalyst
    1.08
     reminder
    1.08
     gateway
    1.07
     conduit
    1.07
     culmination
    1.06
     precursor
    1.04
     testament
    1.01
     tool
    1.00
     beacon
    1.00
     manifestation
    1.00
    Act Density 0.241%

    No Known Activations