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

    Neuronpedia

    INDEX
    Explanations

    mentions of people working or collaborating together

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ichever
    -0.61
    odge
    -0.60
    "}],"
    -0.57
    agogue
    -0.57
    omed
    -0.56
     sterile
    -0.56
    Bind
    -0.56
    bestos
    -0.56
     pestic
    -0.56
    impact
    -0.55
    POSITIVE LOGITS
     tweeting
    1.14
     backstage
    1.10
    ðŁĺ
    1.01
     joking
    0.99
     ðŁĺ
    0.99
     (@
    0.95
     shortly
    0.95
     ðŁij
    0.94
     tonight
    0.94
     onstage
    0.94
    Act Density 0.503%

    No Known Activations