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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating obligation or recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    244
    -0.16
    ichel
    -0.15
    utex
    -0.15
    elop
    -0.15
    lod
    -0.15
    LETTE
    -0.15
    adal
    -0.14
    chedulers
    -0.14
    isin
    -0.14
    eras
    -0.14
    POSITIVE LOGITS
    nt
    0.18
    ramework
    0.18
    ering
    0.15
    eature
    0.15
     be
    0.14
    oun
    0.14
    eatures
    0.14
     Boeh
    0.14
     Slave
    0.14
    /schema
    0.13
    Act Density 0.074%

    No Known Activations