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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and related verb constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ookies
    -0.16
    jadi
    -0.16
    indsight
    -0.16
     Left
    -0.15
    .sessions
    -0.15
    wed
    -0.15
    ällt
    -0.14
    Left
    -0.14
    /left
    -0.14
    ldb
    -0.14
    POSITIVE LOGITS
     required
    0.25
     asked
    0.23
     responsible
    0.21
    ask
    0.20
     expected
    0.19
    chen
    0.19
     encour
    0.19
     divided
    0.19
    enc
    0.18
     encouraged
    0.18
    Act Density 0.050%

    No Known Activations