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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and protective measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Provider
    -0.14
    ulumi
    -0.14
    å²³
    -0.14
    ortex
    -0.14
    olet
    -0.14
    osh
    -0.14
    oulouse
    -0.14
    Å©
    -0.14
    ovah
    -0.14
    asje
    -0.13
    POSITIVE LOGITS
    abra
    0.19
    afen
    0.18
    aken
    0.17
     Tourism
    0.15
    ittel
    0.15
    vest
    0.15
    éĤĬ
    0.15
    alink
    0.14
     neutral
    0.14
    abwe
    0.14
    Act Density 0.004%

    No Known Activations