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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial arrangement or placement

    oai_token-act-pair · gpt-3.5-turbo

    words related to the arrangement or placement of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    burgh
    -0.81
    士
    -0.77
    RESULTS
    -0.76
    clerosis
    -0.72
    odan
    -0.70
    uncture
    -0.69
    alty
    -0.68
    port
    -0.68
    proxy
    -0.67
    idental
    -0.67
    POSITIVE LOGITS
     atop
    0.95
    river
    0.82
     prominently
    0.80
    rily
    0.77
     externally
    0.77
     horizontally
    0.77
     thereto
    0.76
     securely
    0.75
     incorrectly
    0.75
     beneath
    0.74
    Act Density 0.151%

    No Known Activations