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

    Neuronpedia

    INDEX
    Explanations

    references to legal concepts and human rights documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Victorian
    -0.19
    198
    -0.18
     Software
    -0.17
    199
    -0.17
     software
    -0.17
     Millennium
    -0.16
    IDS
    -0.16
     euro
    -0.16
    187
    -0.16
    Software
    -0.15
    POSITIVE LOGITS
    195
    0.63
    194
    0.42
    Û±Û¹Ûµ
    0.41
    196
    0.32
     Eisenhower
    0.27
    Û±Û¹Û´
    0.26
     Truman
    0.23
     Atomic
    0.22
     СÑĤа
    0.21
     Stalin
    0.21
    Act Density 0.368%

    No Known Activations