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

    Neuronpedia

    INDEX
    Explanations

    words related to captivity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to captivity and the condition of captive beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucc
    -0.75
    info
    -0.70
    resso
    -0.70
    arten
    -0.69
    uyomi
    -0.65
    ergy
    -0.65
    izarre
    -0.65
    ension
    -0.64
    ordan
    -0.63
     Foundation
    -0.63
    POSITIVE LOGITS
     captive
    1.47
     captives
    1.24
     hostages
    0.89
    eers
    0.85
     hostage
    0.85
     captivity
    0.84
    racuse
    0.80
     pigeon
    0.79
    Capt
    0.78
     enslaved
    0.76
    Act Density 0.007%

    No Known Activations