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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "national" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ext
    -0.18
    gh
    -0.18
     nice
    -0.17
    ory
    -0.17
     nations
    -0.16
    h
    -0.16
    nice
    -0.15
    ature
    -0.15
     Nations
    -0.15
    eden
    -0.14
    POSITIVE LOGITS
    istic
    0.31
    ities
    0.28
    /local
    0.27
    ized
    0.25
    istically
    0.24
    izing
    0.23
    /reg
    0.23
     anthem
    0.22
    ization
    0.21
    /global
    0.21
    Act Density 0.035%

    No Known Activations