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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "semantics" and its variations or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umlu
    -0.18
    omer
    -0.18
    anela
    -0.17
    ÑģÑĤвоÑĢ
    -0.15
    omain
    -0.15
    yms
    -0.15
    омеÑĢ
    -0.15
    UZ
    -0.15
    iets
    -0.15
    atitude
    -0.15
    POSITIVE LOGITS
    inary
    0.32
    esters
    0.30
    antically
    0.27
    iotics
    0.24
    inars
    0.24
    olina
    0.24
    antics
    0.23
    iotic
    0.23
    estre
    0.22
    per
    0.21
    Act Density 0.007%

    No Known Activations