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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    data manipulation and file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.92
     juſ
    -0.88
     myſelf
    -0.84
     ſch
    -0.77
     ſche
    -0.77
     ſon
    -0.77
     itſelf
    -0.77
     ſtre
    -0.76
     Jefus
    -0.75
     houſe
    -0.75
    POSITIVE LOGITS
    (&:
    0.68
    ->
    0.66
    _->
    0.64
    ']").
    0.64
    ]').
    0.60
    $_.
    0.60
    :].
    0.58
    ']->
    0.55
    "]').
    0.54
    .
    0.54
    Act Density 0.115%

    No Known Activations