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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, possibly related to different contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ivia
    -0.86
    urity
    -0.81
    berus
    -0.78
    gdala
    -0.77
    ãĥĪ
    -0.77
    ctions
    -0.77
    ctory
    -0.75
    ãĥ¤
    -0.75
    alogue
    -0.75
    ãĥ¬
    -0.74
    POSITIVE LOGITS
    robe
    1.70
    ynski
    0.96
    ens
    0.93
    ages
    0.85
    hips
    0.83
    ings
    0.82
    ell
    0.82
    ling
    0.80
    age
    0.79
    lock
    0.79
    Act Density 0.028%

    No Known Activations