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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks, particularly at the end or in referencing contexts

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

    References in brackets

    np_acts-logits-general · gemini-2.0-flash

    legal citations and quotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.06
     pleaſure
    -1.04
     houſe
    -1.04
     itſelf
    -1.00
     Reſ
    -0.96
     fubject
    -0.96
     ſeveral
    -0.95
     ſind
    -0.94
     greateſt
    -0.93
     purpoſe
    -0.93
    POSITIVE LOGITS
    ↵↵
    1.18
    ↵↵↵
    0.86
    ↵↵↵↵
    0.73
    ↵
    0.71
     The
    0.65
    ↵↵↵↵↵↵
    0.62
    ↵↵↵↵↵
    0.61
    )
    0.59
     or
    0.58
    ).
    0.58
    Act Density 0.569%

    No Known Activations