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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to emotional states or psychological well-being

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional experiences and intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.78
    iago
    -0.75
    nered
    -0.71
    tower
    -0.70
    arent
    -0.70
    emark
    -0.70
    authorized
    -0.69
    etts
    -0.69
    xus
    -0.68
    ateur
    -0.67
    POSITIVE LOGITS
     attachment
    0.94
     roller
    0.94
     maturity
    0.93
     distress
    0.91
     turmoil
    0.88
     contag
    0.87
     outburst
    0.83
     reactions
    0.83
    izing
    0.82
     trauma
    0.81
    Act Density 0.039%

    No Known Activations