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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to formal structures, positions, and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤии
    -0.15
    herits
    -0.15
    EDA
    -0.15
    овÑĸд
    -0.15
    zdy
    -0.14
     باش
    -0.14
    avana
    -0.14
    å°ĺ
    -0.14
    rál
    -0.14
    VED
    -0.14
    POSITIVE LOGITS
     stage
    0.39
    stage
    0.34
     stages
    0.32
    -stage
    0.31
     phase
    0.31
     Stage
    0.30
    Stage
    0.27
    éĺ¶æ®µ
    0.27
    _stage
    0.27
     phases
    0.26
    Act Density 0.029%

    No Known Activations