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

    Neuronpedia

    INDEX
    Explanations

    words related to a position of authority or importance, often in an educational or professional setting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "principal" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.79
    ï¸ı
    -0.67
    urg
    -0.65
    glass
    -0.65
    reens
    -0.65
    ICA
    -0.64
    OPE
    -0.64
    ALTH
    -0.64
    glers
    -0.63
    vim
    -0.63
    POSITIVE LOGITS
    ities
    1.20
     investigator
    0.92
     Investigator
    0.86
    essors
    0.86
    ipal
    0.82
    hetical
    0.80
    ises
    0.77
    holders
    0.76
    ising
    0.75
    ignment
    0.74
    Act Density 0.049%

    No Known Activations