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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines or current events

    oai_token-act-pair · gpt-3.5-turbo

    topics and phrases related to economic issues and political challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.73
     newsp
    -0.63
     inclusive
    -0.58
     specialization
    -0.58
     life
    -0.57
     reserves
    -0.57
     bass
    -0.55
     bearer
    -0.55
     canned
    -0.55
     ideal
    -0.54
    POSITIVE LOGITS
    ccording
    1.04
    ³³³³³³³³³³³³³³³³
    0.82
    Meanwhile
    0.73
    ³³³³³³³³
    0.72
     Experts
    0.70
    ³³³
    0.69
    JUST
    0.68
     Forget
    0.67
    Experts
    0.66
    Earlier
    0.65
    Act Density 0.129%

    No Known Activations