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

    Neuronpedia

    INDEX
    Explanations

    references to signs and signage-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancias
    -0.13
    asti
    -0.12
    oire
    -0.12
    عب
    -0.12
     uzavÅĻ
    -0.12
    utar
    -0.12
    ippet
    -0.12
    .cx
    -0.12
    Realm
    -0.12
    dives
    -0.12
    POSITIVE LOGITS
     signs
    0.48
     signage
    0.42
     sign
    0.41
     Signs
    0.41
     Sign
    0.34
    sign
    0.33
    Sign
    0.31
     SIGN
    0.29
    -sign
    0.29
     directional
    0.28
    Act Density 0.044%

    No Known Activations