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

    Neuronpedia

    INDEX
    Explanations

    expressions related to sharing information or findings with others

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate sharing or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cussion
    -0.72
    venant
    -0.71
    formation
    -0.69
    steen
    -0.67
    itures
    -0.67
    pmwiki
    -0.66
     vacc
    -0.65
    verage
    -0.62
     trail
    -0.61
    orius
    -0.61
    POSITIVE LOGITS
     fellow
    0.98
     coworkers
    0.89
     regard
    0.87
    stood
    0.87
     us
    0.87
     passers
    0.86
     classmates
    0.86
     colleagues
    0.84
     regards
    0.82
     peers
    0.80
    Act Density 0.056%

    No Known Activations