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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to abstract concepts such as senses, feelings, and perceptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate different aspects of perception or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sites
    -0.83
    ttes
    -0.80
    die
    -0.75
    nr
    -0.74
    esan
    -0.73
    iaries
    -0.72
    heid
    -0.70
    olicy
    -0.70
    ansas
    -0.70
    orst
    -0.70
    POSITIVE LOGITS
     urgency
    1.19
     humor
    0.95
     warmth
    0.94
     humour
    0.94
     nostalgia
    0.88
     insecurity
    0.88
     existential
    0.88
     optimism
    0.86
     parity
    0.84
     patriotism
    0.84
    Act Density 0.077%

    No Known Activations