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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vais
    -0.18
    asti
    -0.17
     unm
    -0.16
    rais
    -0.16
     Richardson
    -0.16
     gettext
    -0.15
    .tm
    -0.14
    ador
    -0.14
    seau
    -0.14
    inois
    -0.14
    POSITIVE LOGITS
    mos
    0.17
    iets
    0.15
     Mountain
    0.15
    uppe
    0.14
    .Tensor
    0.14
    .GL
    0.14
    oload
    0.14
    éĺµ
    0.14
    Strict
    0.14
    лиÑĤ
    0.14
    Act Density 0.081%

    No Known Activations