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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of immovability or the idea of things being unchangeable or static

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uyomi
    -1.18
     Seym
    -1.03
     Cosponsors
    -0.99
     unchecked
    -0.98
    */(
    -0.98
     Warfare
    -0.93
     dams
    -0.90
    Ĥ¬
    -0.90
    ffiti
    -0.89
     behav
    -0.88
    POSITIVE LOGITS
    aterial
    1.53
    obile
    1.47
    ovable
    1.43
    agine
    1.40
    igrant
    1.39
    ersion
    1.37
    igrants
    1.35
    igrated
    1.34
    ittal
    1.31
    ersive
    1.27
    Act Density 1.431%

    No Known Activations