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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences expressing strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong positive feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.75
    heid
    -0.75
    ansas
    -0.72
    lain
    -0.70
    ucky
    -0.68
    throp
    -0.68
    oire
    -0.67
    reath
    -0.66
    utions
    -0.66
    allas
    -0.65
    POSITIVE LOGITS
     darn
    0.80
     appreciated
    0.79
     bothered
    0.78
    FTWARE
    0.78
     liked
    0.76
     bothering
    0.74
     distressed
    0.73
     needed
    0.72
     appreciate
    0.72
    ignment
    0.71
    Act Density 0.043%

    No Known Activations