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

    Neuronpedia

    INDEX
    Explanations

    descriptors indicating the quality or significance of nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olen
    -0.21
    acco
    -0.18
    iesel
    -0.15
    oli
    -0.15
    formance
    -0.14
    ivery
    -0.14
    rava
    -0.14
    ãĥ¬ãĥ³
    -0.14
    arine
    -0.14
    alore
    -0.13
    POSITIVE LOGITS
     tendency
    0.23
     vested
    0.22
     knack
    0.21
     history
    0.21
     duty
    0.20
     obligation
    0.20
     vend
    0.20
     problem
    0.19
     responsibility
    0.19
     habit
    0.19
    Act Density 0.159%

    No Known Activations