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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interactive elements in video games

    oai_token-act-pair · gpt-3.5-turbo

    terms related to player and game functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ologies
    -0.86
    olog
    -0.84
    omen
    -0.78
    thodox
    -0.77
    romy
    -0.77
    stra
    -0.77
    rieg
    -0.76
    arius
    -0.75
    rav
    -0.75
    str
    -0.74
    POSITIVE LOGITS
    lihood
    0.97
    halla
    0.84
     playable
    0.77
    ATURES
    0.76
    Characters
    0.72
    isable
    0.71
     usable
    0.68
    ãĤ
    0.68
    ATURE
    0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.68
    Act Density 0.032%

    No Known Activations