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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the introduction of new concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     har
    -0.18
    azon
    -0.16
     Commod
    -0.15
    uld
    -0.15
    دÙĨ
    -0.15
    aret
    -0.14
    ha
    -0.14
     equ
    -0.14
     pigeon
    -0.14
     onward
    -0.14
    POSITIVE LOGITS
    ductory
    0.17
    erif
    0.16
    afx
    0.16
    chine
    0.15
    /request
    0.14
    kovi
    0.14
    ovu
    0.14
    931
    0.14
    mrt
    0.14
    prising
    0.14
    Act Density 0.028%

    No Known Activations