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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative emotional states, particularly loneliness

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to loneliness and solitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.90
    ropri
    -0.83
    ulate
    -0.82
    rity
    -0.79
    emark
    -0.77
    aminer
    -0.77
    ulin
    -0.76
    assador
    -0.76
    tarians
    -0.73
    ruction
    -0.71
    POSITIVE LOGITS
     confinement
    0.89
    oneliness
    0.83
     lonely
    0.83
    lust
    0.76
     Hots
    0.74
     loneliness
    0.72
     melancholy
    0.70
     melanch
    0.69
     bere
    0.68
     consolation
    0.68
    Act Density 0.036%

    No Known Activations