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

    Neuronpedia

    INDEX
    Explanations

    names that end with "vich" or "wicz"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    anger
    -0.81
    rim
    -0.71
    angers
    -0.68
     Rugby
    -0.65
    mare
    -0.63
    Champ
    -0.63
    ANG
    -0.63
    ANGE
    -0.63
    acy
    -0.62
    Opt
    -0.62
    POSITIVE LOGITS
    vich
    3.50
    wic
    1.65
    л
    1.61
    zinski
    1.19
    vic
    1.12
    pta
    1.10
    witz
    1.10
     seated
    1.08
    cki
    1.03
    castle
    1.00
    Act Density 0.061%

    No Known Activations