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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unity, collective actions, and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing collective identity and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Weather
    -0.72
    rouse
    -0.72
    Decl
    -0.63
    rophe
    -0.60
    etz
    -0.59
    sky
    -0.58
    Disk
    -0.58
     Ars
    -0.57
    Storm
    -0.57
     Sierra
    -0.56
    POSITIVE LOGITS
     gonna
    0.72
     ðŁij
    0.72
    âĺ
    0.72
    selves
    0.66
    \\
    0.65
    puter
    0.63
    ãĥ¼ãĥ«
    0.63
    .''
    0.63
     â
    0.63
    ĵĺ
    0.62
    Act Density 0.113%

    No Known Activations