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

    Neuronpedia

    INDEX
    Explanations

    the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kral
    -0.16
     Royale
    -0.16
    ocular
    -0.15
    .dm
    -0.15
    ikan
    -0.15
     Yani
    -0.15
    éĥİ
    -0.14
    chedulers
    -0.14
    -pencil
    -0.14
     Sous
    -0.14
    POSITIVE LOGITS
    sun
    0.15
    ossa
    0.15
    reb
    0.14
    DownList
    0.14
     accents
    0.14
     Hamp
    0.14
    pu
    0.13
    estre
    0.13
     interfer
    0.13
    ustin
    0.13
    Act Density 0.012%

    No Known Activations