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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "love" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erer
    -0.19
    ubern
    -0.17
    ucer
    -0.16
    anker
    -0.16
    alist
    -0.15
    auf
    -0.15
    ÃľRK
    -0.15
    Ñĥки
    -0.15
    eker
    -0.15
    ermen
    -0.14
    POSITIVE LOGITS
    eland
    0.30
    eliness
    0.29
    ett
    0.27
    ell
    0.25
    esome
    0.24
    ely
    0.24
    estr
    0.23
    estone
    0.23
    ells
    0.22
    emarks
    0.22
    Act Density 0.006%

    No Known Activations