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

    Neuronpedia

    INDEX
    Explanations

    statements that indicate opinions or observations from individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥĥãĤ¯
    -0.15
    eday
    -0.15
    acas
    -0.15
     Stacy
    -0.15
    .infinity
    -0.14
    tape
    -0.14
    åŃĺäºİ
    -0.14
    UNS
    -0.14
    Ïīν
    -0.14
    thood
    -0.13
    POSITIVE LOGITS
     himself
    0.15
    lingen
    0.15
     gor
    0.14
     gene
    0.14
    ENUM
    0.14
    Į
    0.14
     who
    0.13
    ymi
    0.13
    ови
    0.13
     lifelong
    0.13
    Act Density 0.052%

    No Known Activations