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

    Neuronpedia

    INDEX
    Explanations

    medical and pharmaceutical terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ocamp
    -0.81
     respectively
    -0.79
    SPONSORED
    -0.77
    etheless
    -0.73
    ahime
    -0.73
    ãĤ´ãĥ³
    -0.73
     constitu
    -0.72
     fundament
    -0.70
     Canaver
    -0.68
     juven
    -0.67
    POSITIVE LOGITS
    Rocket
    0.63
    ico
    0.59
    ton
    0.56
     Rocket
    0.56
     physicist
    0.55
    hack
    0.54
    stock
    0.54
     Gamma
    0.52
     stiff
    0.51
     Suzuki
    0.51
    Act Density 11.816%

    No Known Activations