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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of following or tracking

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or character, particularly in the context of narratives or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneers
    -1.01
    ãģĨ
    -1.00
    ividual
    -0.91
    raints
    -0.90
    MODE
    -0.86
    acca
    -0.83
    iosyncr
    -0.82
    ãĥ¼ãĥĨ
    -0.81
    etheless
    -0.80
    éĹĺ
    -0.79
    POSITIVE LOGITS
    icester
    1.20
    isure
    1.03
    opard
    0.96
    agues
    0.95
    lean
    0.94
    ather
    0.91
    Bron
    0.85
    ttes
    0.85
    lla
    0.84
    aky
    0.81
    Act Density 0.007%

    No Known Activations