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

    Neuronpedia

    INDEX
    Explanations

    terms related to non-homogeneity or variations in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NonNull
    -0.16
    ovich
    -0.15
     VIP
    -0.15
    onica
    -0.14
     Indo
    -0.14
    dra
    -0.14
    yb
    -0.14
    agu
    -0.14
    å°ļ
    -0.14
    utton
    -0.14
    POSITIVE LOGITS
    line
    0.23
    tr
    0.23
    local
    0.20
     trivial
    0.20
    van
    0.20
    station
    0.20
    compact
    0.20
    liner
    0.20
    adi
    0.19
    antic
    0.19
    Act Density 0.016%

    No Known Activations