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

    Neuronpedia

    INDEX
    Explanations

    legal terms and conditions related to user agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SE
    -0.28
    SY
    -0.25
    SW
    -0.25
    ï¼³
    -0.25
    sy
    -0.24
    SUP
    -0.24
    SH
    -0.24
    ãĤ»
    -0.24
    SG
    -0.24
    Sy
    -0.24
    POSITIVE LOGITS
     sinister
    0.31
     sincerely
    0.30
     solely
    0.30
     smell
    0.29
     situated
    0.29
     satisfy
    0.29
     synonymous
    0.29
     suggest
    0.29
     sincere
    0.29
     sooner
    0.29
    Act Density 0.177%

    No Known Activations