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

    Neuronpedia

    INDEX
    Explanations

    items and actions related to a fantasy game setting, potentially involving combat and spells

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.65
    ername
    -0.61
    guyen
    -0.60
    ãĥķãĤ¡
    -0.60
     veter
    -0.58
     GOODMAN
    -0.57
    ãĥ¼ãĥĨãĤ£
    -0.57
    combe
    -0.56
    itton
    -0.55
    ãĥ¼ãĥĨ
    -0.54
    POSITIVE LOGITS
     elephants
    0.66
     demons
    0.65
     emperor
    0.65
    aged
    0.60
     demonic
    0.60
    aging
    0.59
     blink
    0.58
     wolves
    0.57
     hydra
    0.56
     pandemonium
    0.56
    Act Density 12.501%

    No Known Activations