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

    Neuronpedia

    INDEX
    Explanations

    references to government actions, policies, and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     society
    -0.15
    IRM
    -0.15
    oppable
    -0.15
    ulumi
    -0.14
    ety
    -0.14
    ataire
    -0.14
    IMS
    -0.14
    rk
    -0.14
    ffective
    -0.14
    ociety
    -0.14
    POSITIVE LOGITS
     Light
    0.16
    iffe
    0.15
    ιθ
    0.15
    rote
    0.15
    skins
    0.15
    914
    0.14
    spread
    0.14
    965
    0.14
    les
    0.14
    arm
    0.14
    Act Density 0.606%

    No Known Activations