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

    Neuronpedia

    INDEX
    Explanations

    instances of precision and exactness in descriptions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.62
    Autoritní
    -0.58
     necessariamente
    -0.56
     createSlice
    -0.55
    ншни
    -0.54
     completamente
    -0.54
    とにかく
    -0.53
     addirittura
    -0.53
    IndentedString
    -0.52
     basically
    -0.52
    POSITIVE LOGITS
     same
    0.81
     opposite
    0.80
    LEncoder
    0.68
    saraba
    0.67
    same
    0.67
     Same
    0.63
     replicas
    0.63
    Ditto
    0.63
    opposite
    0.62
     replica
    0.61
    Act Density 0.102%

    No Known Activations