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

    Neuronpedia

    INDEX
    Explanations

    phrases describing containment or restriction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contained."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrim
    -0.83
    issance
    -0.76
    si
    -0.75
    kins
    -0.66
    edes
    -0.65
    yers
    -0.65
    agent
    -0.64
    ingo
    -0.63
    ingham
    -0.63
     tilt
    -0.61
    POSITIVE LOGITS
     contained
    0.84
     Contains
    0.78
    nces
    0.75
    poons
    0.75
     contains
    0.73
    encies
    0.73
    ĸļ
    0.72
     therein
    0.72
     herein
    0.71
    uggest
    0.71
    Act Density 0.011%

    No Known Activations