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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions of taking someone somewhere or taking a photo

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.79
    icion
    -0.70
    cess
    -0.65
    ept
    -0.64
    itated
    -0.61
    riot
    -0.61
    ificent
    -0.60
    raid
    -0.60
    regate
    -0.60
    erie
    -0.59
    POSITIVE LOGITS
     hostage
    1.29
     aback
    1.24
     seriously
    1.11
     away
    1.02
     apart
    0.98
     Seriously
    0.98
     captive
    0.94
     prisoner
    0.93
     offline
    0.92
     into
    0.88
    Act Density 0.119%

    No Known Activations