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

    Neuronpedia

    INDEX
    Explanations

    names or references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń
    -3.03
    §
    -2.71
    Ĺ
    -2.62
    ³
    -2.55
    «
    -2.50
    Ĭ
    -2.43
    ·¸
    -2.38
    ĥ
    -2.36
    ľ
    -2.29
    ¬
    -2.26
    POSITIVE LOGITS
    nel
    2.51
    nal
    1.89
    aho
    1.86
    arman
    1.76
    ville
    1.76
    uscript
    1.73
    ault
    1.73
    agem
    1.69
    stru
    1.68
    nas
    1.66
    Act Density 0.232%

    No Known Activations