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

    Neuronpedia

    INDEX
    Explanations

    references to different schemes or frameworks within a scientific context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EAT
    -0.87
     Horton
    -0.78
    ism
    -0.70
     Hati
    -0.68
     eat
    -0.67
    pula
    -0.66
    EAT
    -0.65
    mort
    -0.64
    eat
    -0.64
    nat
    -0.63
    POSITIVE LOGITS
     SCHEME
    1.73
     Schemes
    1.70
    scheme
    1.70
    schemes
    1.69
    Scheme
    1.68
     schemes
    1.65
    Schemes
    1.61
     Scheme
    1.60
     scheme
    1.58
    SCHEME
    1.58
    Act Density 0.014%

    No Known Activations