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

    Neuronpedia

    INDEX
    Explanations

    phrases related to control and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    overlap
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
    ond
    -0.14
    yat
    -0.14
    grave
    -0.13
    onders
    -0.13
    ioned
    -0.13
    antages
    -0.13
    192
    -0.13
    odynam
    -0.13
    POSITIVE LOGITS
     destiny
    0.43
     fate
    0.36
     destin
    0.36
     Destiny
    0.32
     Fate
    0.30
     destino
    0.29
     affairs
    0.27
     decisions
    0.27
     direction
    0.26
     outcome
    0.26
    Act Density 0.186%

    No Known Activations