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

    Neuronpedia

    INDEX
    Explanations

    concepts related to linear equations and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лив
    -0.15
    amax
    -0.15
    urv
    -0.15
     cục
    -0.15
     Cum
    -0.15
    eval
    -0.15
    ibo
    -0.15
    ib
    -0.15
    ein
    -0.15
    ek
    -0.14
    POSITIVE LOGITS
    coln
    0.25
    ized
    0.22
    ities
    0.20
    izing
    0.20
    arity
    0.19
    ization
    0.19
    izable
    0.19
    shire
    0.19
    /qu
    0.18
    ette
    0.17
    Act Density 0.016%

    No Known Activations