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

    Neuronpedia

    INDEX
    Explanations

    concepts related to subjective importance and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.34
    s
    -0.31
    тро
    -0.30
    “
    -0.30
     "
    -0.30
    "
    -0.29
    <eos>
    -0.29
     devriez
    -0.29
     sigo
    -0.28
    不
    -0.28
    POSITIVE LOGITS
     témoig
    0.76
     queſta
    0.72
     beſch
    0.72
     Normdatei
    0.70
    idlertid
    0.69
    aimeJ
    0.69
    ſelben
    0.68
    ſcher
    0.68
    ロウィン
    0.68
    باردا
    0.68
    Act Density 0.042%

    No Known Activations