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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "different."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iversit
    -0.17
    igan
    -0.16
     oppos
    -0.15
    frey
    -0.14
    IDD
    -0.14
     doubt
    -0.14
    виÑĩ
    -0.14
    780
    -0.13
    .bundle
    -0.13
    ãĥ³ãĥĢ
    -0.13
    POSITIVE LOGITS
    iability
    0.22
    iating
    0.19
    ials
    0.18
    iates
    0.18
    iale
    0.18
     pied
    0.16
    achs
    0.16
    elf
    0.16
    iator
    0.15
    iators
    0.15
    Act Density 0.059%

    No Known Activations