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

    Neuronpedia

    INDEX
    Explanations

    the infinitive form of verbs, particularly the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ds
    -0.14
    rael
    -0.14
    ãĤ¤ãĥ³ãĥĪ
    -0.14
    icamente
    -0.13
    uf
    -0.13
    å®ĭä½ĵ
    -0.13
    ANJI
    -0.13
    ẽ
    -0.13
    esi
    -0.13
    ikal
    -0.13
    POSITIVE LOGITS
    -bodied
    0.21
    /disable
    0.18
    tings
    0.17
    asty
    0.17
    berra
    0.15
    γή
    0.15
    NullException
    0.15
    ister
    0.15
    oten
    0.15
     bod
    0.14
    Act Density 0.037%

    No Known Activations