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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proximity or closeness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    NZ
    -0.77
    FAQ
    -0.69
    wine
    -0.69
    ulations
    -0.68
    ONES
    -0.67
    cloth
    -0.66
    ;;;;;;;;;;;;
    -0.66
    \\\\\\\\
    -0.65
    orie
    -0.64
    otte
    -0.63
    POSITIVE LOGITS
     than
    1.11
    than
    1.10
     Than
    0.94
     scrutiny
    0.94
     proximity
    0.90
     examination
    0.88
     "$:/
    0.84
     resemblance
    0.83
     thereto
    0.82
     inspection
    0.80
    Act Density 0.014%

    No Known Activations