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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or commands

    oai_token-act-pair · gpt-3.5-turbo

    instructions or commands related to software setup and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     starving
    -0.71
     dispers
    -0.66
     tram
    -0.62
     dope
    -0.62
     stunt
    -0.61
     fost
    -0.60
     feud
    -0.59
    killed
    -0.58
     riot
    -0.57
    åħī
    -0.57
    POSITIVE LOGITS
     Scroll
    1.19
     click
    1.16
     Browse
    1.13
    Scroll
    1.11
     scroll
    1.10
     navigate
    1.05
    select
    1.03
     Click
    1.02
     Select
    1.02
     select
    1.00
    Act Density 0.153%

    No Known Activations