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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the existence or state of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.70
    󠁣
    -0.60
     snippetHide
    -0.60
    ロウィン
    -0.59
     témoig
    -0.57
     myſelf
    -0.57
     față
    -0.56
     zasi
    -0.56
    ementara
    -0.55
    <unused23>
    -0.54
    POSITIVE LOGITS
     é
    1.23
     ed
    0.84
     е
    0.60
    AndEndTag
    0.51
     É
    0.44
    被
    0.43
     eds
    0.42
     foi
    0.41
     ré
    0.40
    .-
    0.38
    Act Density 0.117%

    No Known Activations