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

    Neuronpedia

    INDEX
    Explanations

    instructions or advice in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    instructions or guidance related to software settings and troubleshooting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pires
    -0.78
    åħī
    -0.75
    arious
    -0.74
     Drawn
    -0.70
    ody
    -0.68
     Kinnikuman
    -0.67
    punk
    -0.65
    arthed
    -0.64
     Mong
    -0.64
    blooded
    -0.64
    POSITIVE LOGITS
     uninstall
    1.68
     disable
    1.51
     restart
    1.34
     delete
    1.31
     manually
    1.24
     reset
    1.22
     reload
    1.20
     reboot
    1.20
     revert
    1.19
     reopen
    1.16
    Act Density 0.195%

    No Known Activations