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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical proximity or closeness

    oai_token-act-pair · gpt-3.5-turbo

    references to physical closeness or nearness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tek
    -0.71
    hari
    -0.71
    OY
    -0.70
    sol
    -0.69
    ifter
    -0.69
    boys
    -0.68
    err
    -0.65
    tails
    -0.64
    boy
    -0.63
    orah
    -0.63
    POSITIVE LOGITS
     thereto
    1.23
    mble
    0.84
    xual
    0.80
     proximity
    0.78
    imity
    0.76
    alty
    0.75
    heid
    0.74
    ement
    0.73
    ï¸
    0.71
    xus
    0.71
    Act Density 0.046%

    No Known Activations