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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussion or argumentation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to ethics and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soon
    -0.60
    âĦ¢
    -0.55
     âĢİ
    -0.55
    iasco
    -0.54
    Sadly
    -0.54
    forums
    -0.50
     Alas
    -0.49
    FAQ
    -0.49
    wild
    -0.49
    Offline
    -0.49
    POSITIVE LOGITS
     sidx
    0.57
     refere
    0.57
    itialized
    0.55
    tains
    0.54
     attachment
    0.50
     preference
    0.49
     initi
    0.49
     counterpart
    0.49
    tained
    0.49
     assists
    0.48
    Act Density 0.885%

    No Known Activations