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

    Neuronpedia

    INDEX
    Explanations

    language associated with addiction and recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TEL
    -0.16
    ixin
    -0.15
     Mü
    -0.15
    ÙĪÙĪ
    -0.15
    ewe
    -0.15
    TE
    -0.14
    MBER
    -0.14
    еж
    -0.14
    imd
    -0.14
    871
    -0.14
    POSITIVE LOGITS
     Alcohol
    0.22
     sober
    0.22
     Grape
    0.21
     AA
    0.20
    sob
    0.19
     sob
    0.18
     Recovery
    0.17
     recovery
    0.17
    -AA
    0.17
     anonymity
    0.17
    Act Density 0.004%

    No Known Activations