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

    Neuronpedia

    INDEX
    Explanations

    references to expertise and efforts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abis
    -0.17
    lernen
    -0.16
    ossa
    -0.16
    indre
    -0.15
     welcome
    -0.14
    оÑĤÑĮ
    -0.14
    alarm
    -0.14
    ialis
    -0.14
    ghest
    -0.14
    ÏĬκ
    -0.14
    POSITIVE LOGITS
     positive
    0.16
     Neg
    0.16
     proud
    0.16
    lio
    0.15
     realized
    0.15
     happy
    0.15
    happy
    0.15
     Positive
    0.15
     easy
    0.15
     Reflect
    0.15
    Act Density 0.010%

    No Known Activations