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

    Neuronpedia

    INDEX
    Explanations

    words related to furniture or objects within a room

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipolar
    -0.77
    EGIN
    -0.77
    irlf
    -0.77
    Reloaded
    -0.72
    fml
    -0.67
    ruary
    -0.67
    Secure
    -0.67
    itely
    -0.66
    Lens
    -0.63
    ARGET
    -0.62
    POSITIVE LOGITS
    hesion
    0.71
    agers
    0.68
     Cemetery
    0.66
    rors
    0.63
    plates
    0.62
     Beet
    0.62
    ings
    0.60
    bys
    0.59
    giene
    0.58
    hers
    0.57
    Act Density 0.970%

    No Known Activations