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

    Neuronpedia

    INDEX
    Explanations

    terms associated with roles and functions in organizational or diplomatic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lian
    -0.15
    ening
    -0.14
    idy
    -0.14
    melon
    -0.14
    mel
    -0.14
    ollo
    -0.14
    ishments
    -0.14
    _VC
    -0.14
    dump
    -0.14
    itan
    -0.14
    POSITIVE LOGITS
    -agent
    0.17
     capped
    0.17
     provoc
    0.17
     cap
    0.16
    ëĭĺ
    0.15
     agent
    0.15
    bidden
    0.14
    oven
    0.14
    .changed
    0.14
    zy
    0.14
    Act Density 0.105%

    No Known Activations