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

    Neuronpedia

    INDEX
    Explanations

    phrases related to online platforms or companies

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude or summarize thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sway
    -0.80
     idle
    -0.80
     reflex
    -0.78
     silent
    -0.76
     selfie
    -0.75
     induct
    -0.75
     unstoppable
    -0.74
     freezer
    -0.74
     cradle
    -0.74
     slow
    -0.74
    POSITIVE LOGITS
    com
    1.19
    org
    1.10
    Org
    1.10
     However
    1.07
    gov
    1.06
    exe
    1.06
    prototype
    1.06
     Additionally
    1.05
    COM
    1.03
    edu
    1.02
    Act Density 0.603%

    No Known Activations