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

    Neuronpedia

    INDEX
    Explanations

    sequences with the special character "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    components of technology announcements and product specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifes
    -0.80
     pard
    -0.75
     intervened
    -0.74
     legally
    -0.74
     equival
    -0.70
     marching
    -0.68
     lived
    -0.67
     intervene
    -0.67
     lawfully
    -0.67
     reflex
    -0.67
    POSITIVE LOGITS
    ccording
    1.06
    Speaking
    1.03
    Liquid
    1.02
    Hardware
    1.01
    Update
    0.96
    AMD
    0.96
    Official
    0.95
    Intel
    0.95
    FU
    0.95
    Meanwhile
    0.94
    Act Density 0.690%

    No Known Activations