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

    Neuronpedia

    INDEX
    Explanations

    person names starting with "Mir" followed by a number

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Primordial
    -0.86
     Panther
    -0.80
    jack
    -0.79
     ASC
    -0.79
    ãģ¦
    -0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
     USPS
    -0.76
    CLASSIFIED
    -0.75
     Donkey
    -0.74
     carriers
    -0.74
    POSITIVE LOGITS
    rors
    1.25
    erity
    1.22
    atis
    1.22
    antics
    1.13
    ents
    1.12
    ig
    1.10
    abilia
    1.10
    izons
    1.09
    annah
    1.05
    imet
    1.05
    Act Density 2.471%

    No Known Activations