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

    Neuronpedia

    INDEX
    Explanations

    spells or spell-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.83
    Reviewer
    -0.82
    phia
    -0.75
    ļéĨĴ
    -0.75
    algia
    -0.75
    Īè
    -0.74
     Wem
    -0.72
    ĺħ
    -0.71
    pheus
    -0.71
    olitan
    -0.69
    POSITIVE LOGITS
    caster
    1.31
    casters
    1.29
    casting
    1.26
    binding
    1.23
    sword
    0.95
     caster
    0.94
     spell
    0.92
    blade
    0.90
    craft
    0.89
     spells
    0.87
    Act Density 0.076%

    No Known Activations