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

    Neuronpedia

    INDEX
    Explanations

    fantasy creatures and items

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oire
    -0.18
    ité
    -0.15
    idental
    -0.14
    atem
    -0.14
    ative
    -0.14
    ceiver
    -0.13
    ory
    -0.13
    notations
    -0.13
    endiary
    -0.13
    icative
    -0.13
    POSITIVE LOGITS
    Reviewer
    0.15
     ourselves
    0.14
    keeping
    0.14
     Spaces
    0.13
     Fever
    0.13
    Kit
    0.13
     Moons
    0.12
     hosp
    0.12
     brut
    0.12
     Seg
    0.12
    Act Density 6.037%

    No Known Activations