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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations, particularly related to inequalities and matrix operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.64
    Personendaten
    -0.59
    Ț
    -0.56
     Indic
    -0.54
    ^*$
    -0.54
    Indic
    -0.50
    |$.
    -0.50
    }^{*}$
    -0.49
    ?\\
    -0.49
    umplimiento
    -0.49
    POSITIVE LOGITS
     =
    0.85
    =
    0.72
    ніципалі
    0.63
     GenerationType
    0.59
    DATABASES
    0.56
     is
    0.54
    Зноскі
    0.53
     ProtoMessage
    0.53
    ţion
    0.52
     leksikon
    0.52
    Act Density 1.724%

    No Known Activations