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

    Neuronpedia

    INDEX
    Explanations

    negations or terms indicating disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     negru
    -0.41
    さすがに
    -0.38
    Risultati
    -0.36
    jface
    -0.36
     ailleurs
    -0.36
     mesmas
    -0.35
     gră
    -0.35
    สาม
    -0.35
     munc
    -0.35
    ごめん
    -0.34
    POSITIVE LOGITS
     lenker
    0.51
     autorytatywna
    0.50
    HostException
    0.48
     invokingState
    0.47
    sizeCache
    0.46
    bcryptjs
    0.45
     lå
    0.44
    NewGuid
    0.44
    ThroughAttribute
    0.44
    Autoritní
    0.44
    Act Density 0.204%

    No Known Activations