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

    Neuronpedia

    INDEX
    Explanations

    highly significant numerical values or patterns

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

    ordinal numbers

    np_acts-logits-general · gemini-2.0-flash

    9th

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }));
    -1.12
    ]));
    -1.11
     pleaſure
    -1.09
     Majefty
    -1.06
     onPostExecute
    -1.03
     ſche
    -1.02
     ſtate
    -0.98
     Anſ
    -0.96
     ſtre
    -0.95
     Reſ
    -0.95
    POSITIVE LOGITS
    1
    0.69
    4
    0.59
     
    0.57
    2
    0.55
    0
    0.54
    6
    0.54
    3
    0.54
    7
    0.53
    5
    0.53
    8
    0.52
    Act Density 0.178%

    No Known Activations