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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of putting or physically arranging objects

    oai_token-act-pair · gpt-3.5-turbo

    references to actions involving placing or positioning entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.62
    ority
    -0.60
    days
    -0.60
     Heist
    -0.59
     sqor
    -0.57
    arious
    -0.56
    bidden
    -0.56
    ALSE
    -0.56
    oris
    -0.55
    Container
    -0.55
    POSITIVE LOGITS
     aside
    0.94
     squarely
    0.89
     together
    0.82
     into
    0.80
     smack
    0.77
     firmly
    0.77
     toget
    0.76
     "$:/
    0.75
     finishing
    0.73
     onto
    0.71
    Act Density 0.154%

    No Known Activations