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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating simplicity or ease of doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelIndex
    -0.16
    ics
    -0.15
    emi
    -0.15
    Å¡ov
    -0.14
    iolet
    -0.14
    ICS
    -0.13
     Tham
    -0.13
    ète
    -0.13
     ever
    -0.13
    ovnÃŃ
    -0.13
    POSITIVE LOGITS
     dÃłng
    0.26
     Easily
    0.19
     easily
    0.18
    -access
    0.16
    aus
    0.16
    amba
    0.16
    forgettable
    0.15
     spotted
    0.15
    accessible
    0.15
    upiter
    0.14
    Act Density 0.063%

    No Known Activations