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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and phrases indicating uncertainty or reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ór
    -0.15
    :animated
    -0.15
    anton
    -0.15
    uib
    -0.14
    dz
    -0.14
    à¤Łà¤ķ
    -0.14
    oka
    -0.13
    imbus
    -0.13
    ores
    -0.13
    Äĩ
    -0.13
    POSITIVE LOGITS
    олом
    0.15
     SEA
    0.14
    damage
    0.13
    isky
    0.13
     DAMAGE
    0.13
    ÄĽn
    0.13
    Jamie
    0.13
    ropy
    0.13
    790
    0.13
     Cov
    0.13
    Act Density 0.009%

    No Known Activations