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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructive actions and learning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _topology
    -0.15
    roat
    -0.15
    olle
    -0.15
    indr
    -0.15
     torch
    -0.15
    TIM
    -0.14
    asca
    -0.14
    dech
    -0.14
    -pdf
    -0.14
    ording
    -0.14
    POSITIVE LOGITS
     establishing
    0.16
    uri
    0.16
     ga
    0.15
    urg
    0.15
     establish
    0.15
     Establishment
    0.15
     establishment
    0.15
    Establish
    0.15
     Ducks
    0.15
    建ç«ĭ
    0.15
    Act Density 0.125%

    No Known Activations