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

    Neuronpedia

    INDEX
    Explanations

    verbs that express desire, intent, or preference

    oai_token-act-pair · gpt-3.5-turbo

    desires and wants expressed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preparations
    -0.65
    imilar
    -0.65
     provisional
    -0.63
     presumption
    -0.61
     Priebus
    -0.60
     Zeit
    -0.58
     Hastings
    -0.58
     schizophren
    -0.57
     fury
    -0.55
    anches
    -0.54
    POSITIVE LOGITS
     dearly
    0.89
    ¶ħ
    0.70
     showcased
    0.69
    ¿½
    0.66
    GB
    0.65
    UGE
    0.65
    ãĤ´
    0.65
    ET
    0.65
    ģĸ
    0.65
    Favorite
    0.65
    Act Density 0.113%

    No Known Activations