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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases that indicate a change in context or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()],
    -0.94
    })`
    -0.90
    ]";
    -0.89
    MigrationBuilder
    -0.88
    ]');
    -0.87
    ')):
    -0.87
    '),
    -0.87
    principalColumn
    -0.86
    '],
    -0.86
    ])/
    -0.84
    POSITIVE LOGITS
    And
    0.88
     And
    0.75
     yes
    0.63
     yeah
    0.62
    Then
    0.56
     hey
    0.53
    일
    0.52
    nd
    0.52
    od
    0.51
     because
    0.51
    Act Density 0.106%

    No Known Activations