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

    Neuronpedia

    INDEX
    Explanations

    titles and headings that refer to significant works or themes in various academic disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wald
    -0.17
     cher
    -0.15
    stell
    -0.15
    abis
    -0.14
    wyn
    -0.14
     equivalent
    -0.14
     Teknik
    -0.14
    wright
    -0.14
     же
    -0.14
     iteration
    -0.14
    POSITIVE LOGITS
    orie
    0.25
    ories
    0.21
    oretical
    0.21
    ore
    0.18
     Role
    0.17
     Roles
    0.16
    orias
    0.16
    ORE
    0.15
    Role
    0.15
    ismet
    0.15
    Act Density 0.083%

    No Known Activations