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

    Neuronpedia

    INDEX
    Explanations

    phrases related to definitions and classifications of terms or concepts, particularly in social and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ink
    -0.15
    sko
    -0.14
    inery
    -0.14
     Rath
    -0.14
    itter
    -0.13
    initWith
    -0.13
    Wildcard
    -0.13
    à¥ģà¤
    -0.13
    crud
    -0.12
     Vib
    -0.12
    POSITIVE LOGITS
     considered
    0.55
     counts
    0.52
     counted
    0.47
     count
    0.45
     Counts
    0.40
    counts
    0.39
     Consider
    0.39
     consider
    0.38
     considers
    0.38
     Count
    0.37
    Act Density 0.322%

    No Known Activations