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

    Neuronpedia

    INDEX
    Explanations

    words related to humility

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hum" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Constructed
    -0.68
    folios
    -0.65
    ãĥī
    -0.62
    hyde
    -0.62
     //[
    -0.62
    okemon
    -0.61
     Dele
    -0.61
     Underground
    -0.60
     harbour
    -0.59
    NetMessage
    -0.58
    POSITIVE LOGITS
    bly
    1.18
    bling
    1.09
    pty
    1.07
     hum
    1.05
    mers
    1.05
    bled
    1.04
    mus
    1.04
    bler
    1.03
    bug
    0.98
    ingly
    0.96
    Act Density 0.014%

    No Known Activations