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

    Neuronpedia

    INDEX
    Explanations

    words related to skepticism or critical viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouse
    -0.17
     Fol
    -0.17
    698
    -0.16
    yun
    -0.15
    tn
    -0.15
    UGE
    -0.15
    rika
    -0.14
    ail
    -0.14
    adx
    -0.14
    mul
    -0.14
    POSITIVE LOGITS
    ptic
    0.29
    letal
    0.25
    chers
    0.20
     Ske
    0.20
    icism
    0.19
    letic
    0.18
    pch
    0.16
     skept
    0.16
    -UA
    0.16
     scept
    0.16
    Act Density 0.007%

    No Known Activations