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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences or stories involving multiple individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of people involved in significant events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.72
    ust
    -0.69
    rap
    -0.65
    stem
    -0.65
    availability
    -0.64
    supp
    -0.64
    é¾įå¥ij士
    -0.63
    enance
    -0.63
    opathy
    -0.62
    heid
    -0.62
    POSITIVE LOGITS
     together
    1.22
     jointly
    1.13
     respectively
    1.12
     collectively
    1.04
    together
    0.94
     Together
    0.93
     toget
    0.92
     themselves
    0.90
     selves
    0.88
     reunion
    0.88
    Act Density 0.961%

    No Known Activations