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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions indicating evasion or avoidance of responsibilities and uncomfortable truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abei
    -0.16
    snap
    -0.15
    itbart
    -0.15
     اÙĦÙħص
    -0.15
    illes
    -0.14
    íĴĪ
    -0.14
    eldorf
    -0.14
    _abort
    -0.14
    mapper
    -0.14
    ãģ£ãģ¨
    -0.14
    POSITIVE LOGITS
     str
    0.16
    akis
    0.15
     cord
    0.15
     distance
    0.15
    Delegate
    0.15
     Distance
    0.15
     peripheral
    0.15
     distances
    0.15
    ordo
    0.14
     Hayward
    0.14
    Act Density 0.021%

    No Known Activations