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

    Neuronpedia

    INDEX
    Explanations

    language related to appreciation and support, especially in the context of online participation and activism

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to community support and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downgrade
    -0.72
     axe
    -0.71
     unsu
    -0.68
     torture
    -0.68
     amput
    -0.68
     faulty
    -0.67
    umbered
    -0.66
     unspecified
    -0.66
     defective
    -0.65
     neglig
    -0.65
    POSITIVE LOGITS
     outreach
    1.04
     outp
    1.00
     grassroots
    0.96
     friendships
    0.94
     Volunte
    0.90
     encouragement
    0.88
     inspires
    0.88
     encouraging
    0.87
     inspiring
    0.86
     awareness
    0.86
    Act Density 1.215%

    No Known Activations