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

    Neuronpedia

    INDEX
    Explanations

    words ending in a specific suffix, "-esh"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "esh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertodd
    -0.85
    é¾įå¥ij士
    -0.82
     carbohyd
    -0.80
    notation
    -0.72
    Frames
    -0.71
     indo
    -0.70
    vernment
    -0.68
     reconc
    -0.68
    eering
    -0.66
    emort
    -0.66
    POSITIVE LOGITS
    merga
    1.48
    adow
    1.19
    awar
    1.05
    nikov
    1.01
    arma
    1.00
    awk
    0.95
    ifter
    0.93
    IFT
    0.91
    ivas
    0.89
    adows
    0.89
    Act Density 0.021%

    No Known Activations