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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their contributions in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     –
    -1.34
    …..
    -1.20
    ……
    -1.07
    ….
    -1.07
    …
    -0.97
    …)
    -0.93
     …..
    -0.92
    …"
    -0.91
    …….
    -0.91
    […]
    -0.90
    POSITIVE LOGITS
     ''
    2.67
    ,''
    2.44
    ''
    2.40
    ?''
    2.39
    .''
    2.36
    ''.
    2.10
    '',
    2.02
    '')
    2.01
     '''
    1.97
     ‘‘
    1.97
    Act Density 0.736%

    No Known Activations