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

    Neuronpedia

    INDEX
    Explanations

    relationships and dependencies in causal models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.59
     dég
    -0.53
     lampada
    -0.51
     bersi
    -0.49
    luß
    -0.48
     Ader
    -0.48
    emang
    -0.48
    헌
    -0.47
    ORTE
    -0.47
     vitesses
    -0.47
    POSITIVE LOGITS
     user
    0.58
     seman
    0.56
    CppCodeGen
    0.55
     latent
    0.54
     inferred
    0.54
     semantic
    0.52
     candidate
    0.51
     query
    0.51
     textual
    0.50
    granate
    0.50
    Act Density 1.278%

    No Known Activations