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

    Neuronpedia

    INDEX
    Explanations

    words related to hostage situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hostage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquette
    -0.83
    alities
    -0.80
    resso
    -0.75
    iferation
    -0.74
    unders
    -0.74
    hesis
    -0.71
    itely
    -0.69
    ril
    -0.67
    orough
    -0.67
    aum
    -0.67
    POSITIVE LOGITS
     hostage
    1.24
     hostages
    1.14
     captive
    0.91
     negotiator
    0.90
     captives
    0.88
     negotiators
    0.85
     kidn
    0.79
     rescue
    0.74
     pets
    0.73
     captivity
    0.73
    Act Density 0.023%

    No Known Activations