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

    Neuronpedia

    INDEX
    Explanations

    words that indicate a specific category or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.23
    thon
    -0.18
    iser
    -0.17
    995
    -0.16
    ãģĤ
    -0.15
    ARSE
    -0.15
    é¸
    -0.15
    s
    -0.15
    sı
    -0.15
    кав
    -0.15
    POSITIVE LOGITS
    opher
    0.21
    otle
    0.21
    ream
    0.20
    otel
    0.20
    ead
    0.20
    ea
    0.19
    ortion
    0.19
    ries
    0.18
    rik
    0.17
    Ø©
    0.17
    Act Density 0.037%

    No Known Activations