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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verse
    -0.16
    verts
    -0.13
    $MESS
    -0.13
    ujet
    -0.13
    rowsable
    -0.13
    .en
    -0.13
    asured
    -0.13
    ãĤĩãģĨ
    -0.13
    æĸ·
    -0.13
    uspend
    -0.12
    POSITIVE LOGITS
    odore
    0.36
    etheless
    0.27
    adays
    0.27
    atre
    0.26
    bsites
    0.24
    atomy
    0.23
    xiety
    0.20
    ÑįÑĤомÑĥ
    0.20
    alog
    0.19
    tlement
    0.19
    Act Density 0.546%

    No Known Activations