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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and contextual cues in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #+#
    -1.10
    dafx
    -1.06
    Хьажоргаш
    -1.06
     незавершена
    -1.04
     ་་
    -1.03
     $_"
    -1.03
     мәкал
    -1.03
    Personendaten
    -1.02
    WriteBarrier
    -1.01
     myſelf
    -1.01
    POSITIVE LOGITS
     
    0.75
    .
    0.66
    <eos>
    0.65
     "
    0.60
    ↵↵
    0.59
    <strong>
    0.59
     A
    0.58
    <
    0.58
    ↵
    0.57
    -
    0.56
    Act Density 1.308%

    No Known Activations