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

    Neuronpedia

    INDEX
    Explanations

    references to communication and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kers
    -0.16
    innen
    -0.15
    AndUpdate
    -0.15
    unately
    -0.14
    iders
    -0.14
    βάλ
    -0.14
     Nhất
    -0.14
    .converter
    -0.14
    lingen
    -0.14
    _mk
    -0.13
    POSITIVE LOGITS
     risk
    0.25
     Risk
    0.23
     risks
    0.23
    risk
    0.22
    Risk
    0.20
     else
    0.20
     risking
    0.19
     otherwise
    0.18
     Ris
    0.17
    -risk
    0.17
    Act Density 0.211%

    No Known Activations