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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or complaints

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to negative actions or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gloss
    -0.69
    ortium
    -0.62
     Bonds
    -0.62
    auga
    -0.61
     Nir
    -0.60
    nown
    -0.60
     Tsukuyomi
    -0.60
     glim
    -0.60
     conspicuous
    -0.59
    ERSON
    -0.59
    POSITIVE LOGITS
    restling
    0.96
    kefeller
    0.79
    backer
    0.79
     Against
    0.68
    igious
    0.67
    boat
    0.67
    hester
    0.65
    Edited
    0.65
    theless
    0.64
     apart
    0.64
    Act Density 0.064%

    No Known Activations