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

    Neuronpedia

    INDEX
    Explanations

    names of individuals who have provided assistance or support

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ilion
    -0.72
     Continued
    -0.72
    Dialogue
    -0.67
    Compar
    -0.66
     elig
    -0.64
    been
    -0.64
    elia
    -0.63
    Activity
    -0.62
    felt
    -0.62
     Prediction
    -0.60
    POSITIVE LOGITS
     organize
    1.34
     propel
    1.28
     organise
    1.27
     establish
    1.24
     create
    1.22
     facilitate
    1.16
     formulate
    1.16
     define
    1.15
     stabilize
    1.15
     elevate
    1.15
    Act Density 0.059%

    No Known Activations