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

    Neuronpedia

    INDEX
    Explanations

    terms related to self-identity and self-sufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ViewData
    -0.15
    SEX
    -0.14
    rab
    -0.14
    zap
    -0.14
    наÑĢ
    -0.14
    icable
    -0.14
    146
    -0.14
     Gang
    -0.14
    une
    -0.14
     Savage
    -0.14
    POSITIVE LOGITS
     reliance
    0.30
     suff
    0.29
     reliant
    0.28
     Suff
    0.26
    -rule
    0.22
     sustaining
    0.20
     sustain
    0.20
     sustainable
    0.20
     rule
    0.20
    çĭ¬ç«ĭ
    0.19
    Act Density 0.013%

    No Known Activations