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

    Neuronpedia

    INDEX
    Explanations

    words related to watching or observing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to water and its management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Surgery
    -0.75
     crush
    -0.71
     crushing
    -0.67
     blunt
    -0.66
     Patent
    -0.62
     Haas
    -0.62
     trauma
    -0.61
     onwards
    -0.60
     Cancer
    -0.60
     MRI
    -0.58
    POSITIVE LOGITS
    chers
    1.47
     wat
    1.43
    wat
    1.43
    cher
    1.07
    terson
    1.03
    aukee
    1.01
    caster
    0.95
    icion
    0.93
    glers
    0.91
    chet
    0.89
    Act Density 0.007%

    No Known Activations