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

    Neuronpedia

    INDEX
    Explanations

    references to physical depth or shallowness in measurements or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to depths and measurements related to underwater or subterranean environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.73
    roma
    -0.73
    ======
    -0.68
    UID
    -0.67
    advertising
    -0.66
    ioch
    -0.66
    OST
    -0.66
    icip
    -0.65
    LM
    -0.64
    DOM
    -0.64
    POSITIVE LOGITS
     depths
    1.26
     caves
    1.04
     canyon
    0.98
     deepest
    0.91
     darkest
    0.91
     dug
    0.89
    waters
    0.88
    deep
    0.86
     lake
    0.86
     gorge
    0.85
    Act Density 0.042%

    No Known Activations