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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cages or enclosures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cages, particularly in relation to animals and their enclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTED
    -0.72
     Bundes
    -0.65
     Done
    -0.61
    evin
    -0.60
    ibel
    -0.60
    vironment
    -0.59
     lender
    -0.58
     FM
    -0.57
    ITNESS
    -0.57
    UD
    -0.56
    POSITIVE LOGITS
     cage
    1.28
     cages
    1.17
     Cage
    1.05
    door
    0.81
    pit
    0.81
    washer
    0.77
     Rampage
    0.75
    eers
    0.74
    Frames
    0.74
     Handler
    0.73
    Act Density 0.007%

    No Known Activations