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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    connections between individual and community experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typo
    -0.65
     Gleaming
    -0.64
     hottest
    -0.63
     Ice
    -0.63
    estamp
    -0.62
     Bullets
    -0.61
    bright
    -0.61
     Clicker
    -0.61
    atical
    -0.60
     START
    -0.60
    POSITIVE LOGITS
     collectively
    1.11
     collective
    1.10
     communal
    1.00
    group
    1.00
     jointly
    0.97
     group
    0.92
     grouped
    0.91
    andem
    0.90
     shared
    0.89
     others
    0.88
    Act Density 0.183%

    No Known Activations