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

    Neuronpedia

    INDEX
    Explanations

    phrases related to serving as a foundation or starting point for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a role or function, particularly involving templates, models, or catalysts for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stan
    -0.72
    itals
    -0.72
    CV
    -0.70
    aeus
    -0.68
    boy
    -0.68
    book
    -0.68
    heart
    -0.67
    wa
    -0.67
    arent
    -0.66
    sth
    -0.64
    POSITIVE LOGITS
     sorts
    0.97
     experimentation
    0.84
     constructing
    0.81
    geries
    0.80
     accessing
    0.75
     spreading
    0.73
     creativity
    0.73
     dissemin
    0.73
     achieving
    0.72
     many
    0.72
    Act Density 0.214%

    No Known Activations