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

    Neuronpedia

    INDEX
    Explanations

    words related to climbing or high altitudes

    oai_token-act-pair · gpt-3.5-turbo

    words related to roles or occupations, specifically those ending in various suffixes typically associated with job titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¯
    -0.67
    ellar
    -0.67
    ENS
    -0.64
    ISON
    -0.64
    angan
    -0.62
    ENSE
    -0.62
    Spons
    -0.62
    ij
    -0.61
    ij士
    -0.61
    herty
    -0.61
    POSITIVE LOGITS
     extraord
    1.50
    esses
    0.98
     beware
    0.95
    ess
    0.88
     who
    0.86
    gery
    0.86
    hip
    0.81
     clad
    0.80
     canoe
    0.77
    doms
    0.74
    Act Density 0.230%

    No Known Activations