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

    Neuronpedia

    INDEX
    Explanations

    words with 'verd' or 'verhagen'

    oai_token-act-pair · gpt-3.5-turbo

    specific suffixes and word endings that evoke intensifiers or descriptive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.68
    ournals
    -0.63
    shapeshifter
    -0.61
    ascus
    -0.58
     backfield
    -0.58
    mercial
    -0.56
    doms
    -0.56
     Jade
    -0.56
    atchewan
    -0.54
     crop
    -0.54
    POSITIVE LOGITS
    illes
    0.87
    imil
    0.86
    ĪĴ
    0.71
    illance
    0.70
    acers
    0.69
    ¨
    0.69
    ilet
    0.69
    Ĭ
    0.68
    osa
    0.68
    fold
    0.67
    Act Density 0.060%

    No Known Activations