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

    Neuronpedia

    INDEX
    Explanations

    references to addiction and withdrawal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fsp
    -0.07
     vess
    -0.07
    ÃŃÅĻ
    -0.07
    ãĥ©ãĥ¼
    -0.07
     trang
    -0.07
     доÑĤ
    -0.07
    iple
    -0.07
    ndl
    -0.07
    inou
    -0.07
    dál
    -0.06
    POSITIVE LOGITS
     withdrawal
    0.20
     Withdraw
    0.17
     withdrawals
    0.17
    withdraw
    0.16
     withdraw
    0.16
    Withdraw
    0.15
     detox
    0.14
     withdrawing
    0.13
     taper
    0.12
     Det
    0.12
    Act Density 0.009%

    No Known Activations