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

    Neuronpedia

    INDEX
    Explanations

    references to newspapers

    oai_token-act-pair · gpt-3.5-turbo

    the term "newspaper" or references to print media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \/
    -0.75
    aris
    -0.72
    \/\/
    -0.71
    thank
    -0.71
    alions
    -0.69
    antes
    -0.66
    BLE
    -0.66
    ihilation
    -0.65
    ographies
    -0.65
    cent
    -0.64
    POSITIVE LOGITS
     intuition
    0.75
     hitch
    0.70
    bath
    0.62
    ALT
    0.61
     intu
    0.59
     overnight
    0.58
    wav
    0.58
     snowball
    0.57
     yogurt
    0.57
     cider
    0.57
    Act Density 0.000%

    No Known Activations