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

    Neuronpedia

    INDEX
    Explanations

    terms related to endorsements or recommendations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.59
     tecnici
    -0.55
     StatefulWidget
    -0.54
    प्
    -0.51
    AAT
    -0.50
    ്
    -0.50
    kirakan
    -0.49
     أبريل
    -0.48
     ayudas
    -0.47
     StatelessWidget
    -0.47
    POSITIVE LOGITS
     endorse
    2.55
     endorsement
    1.93
     endorsing
    1.88
     endorsed
    1.81
     endorsements
    1.67
     Endor
    1.45
    orses
    1.37
    Endor
    1.36
    endor
    1.30
     indor
    1.09
    Act Density 0.000%

    No Known Activations