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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the introduction of new ideas or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     har
    -0.17
    avia
    -0.16
    ög
    -0.15
    ба
    -0.15
    odian
    -0.14
    AZY
    -0.14
     equ
    -0.14
    enstein
    -0.14
    hound
    -0.14
     Hv
    -0.14
    POSITIVE LOGITS
    sted
    0.17
    oler
    0.17
    aca
    0.15
    GBT
    0.15
    DetailsService
    0.14
    anks
    0.14
     Minh
    0.14
    .Utilities
    0.13
     Relax
    0.13
    unnel
    0.13
    Act Density 0.084%

    No Known Activations