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

    Neuronpedia

    INDEX
    Explanations

    references to fundraising

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     widely
    -1.60
    áĢº
    -1.56
    UGH
    -1.55
     heavily
    -1.53
     happier
    -1.51
    blogger
    -1.51
    woke
    -1.50
     stark
    -1.50
    ingle
    -1.49
     sharply
    -1.47
    POSITIVE LOGITS
    ģ
    2.44
    ī
    2.43
    Ħ
    2.41
    ľ
    2.29
    °
    2.25
    ŀ
    2.25
    notes
    2.23
    Ģ
    2.11
    ľĵ
    2.09
    raiser
    2.07
    Act Density 3.190%

    No Known Activations