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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "to be" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovic
    -0.16
    ardless
    -0.15
    kiye
    -0.15
    ÇIJ
    -0.15
    ué
    -0.14
     Cord
    -0.14
    lue
    -0.14
    recht
    -0.14
    ÏĨο
    -0.14
     ren
    -0.14
    POSITIVE LOGITS
    iel
    0.25
    irtual
    0.24
    rot
    0.23
    ÄĻ
    0.23
    roc
    0.21
    ied
    0.20
    iad
    0.20
    iosk
    0.20
    irus
    0.19
    enus
    0.19
    Act Density 0.017%

    No Known Activations