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

    Neuronpedia

    INDEX
    Explanations

    terms related to endorsement and endorsements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    endorse or endorsement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Problem
    -0.50
    Problems
    -0.45
    PROBLE
    -0.45
    problems
    -0.44
     maș
    -0.43
     vectorielle
    -0.42
     Problem
    -0.42
     problem
    -0.41
     problème
    -0.41
     delitos
    -0.41
    POSITIVE LOGITS
     endorsement
    1.98
     endorsed
    1.86
     endorse
    1.83
     Endor
    1.78
     endorsements
    1.75
     endorsing
    1.70
    Endor
    1.66
    endor
    1.59
    orses
    1.23
     indor
    1.07
    Act Density 0.004%

    No Known Activations