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

    Neuronpedia

    INDEX
    Explanations

    references to specific video game titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OAD
    -0.74
    éĹĺ
    -0.74
    IENCE
    -0.73
    ################
    -0.70
    reditary
    -0.68
     obser
    -0.66
    ########
    -0.66
     governors
    -0.66
    aired
    -0.65
    ocene
    -0.65
    POSITIVE LOGITS
    zeb
    0.95
    rice
    0.88
     Dot
    0.83
    dot
    0.82
    zh
    0.81
    rix
    0.76
    lings
    0.75
    gear
    0.74
    tle
    0.74
    wana
    0.74
    Act Density 0.003%

    No Known Activations