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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    853
    -0.18
    arella
    -0.18
    èĤ¥
    -0.16
    oline
    -0.15
    lico
    -0.15
    orno
    -0.15
    qrt
    -0.15
    sortable
    -0.14
     Bald
    -0.14
    ushima
    -0.14
    POSITIVE LOGITS
    iw
    0.17
    adesh
    0.15
     but
    0.15
    ;
    0.15
     deb
    0.14
    206
    0.14
    wan
    0.14
    iyan
    0.14
    ijk
    0.14
    ily
    0.14
    Act Density 0.134%

    No Known Activations