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

    Neuronpedia

    INDEX
    Explanations

    occurrences of special characters and whitespace elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     termica
    -1.11
     Anſ
    -0.98
     varandra
    -0.98
     xenia
    -0.98
     feroit
    -0.96
     myſelf
    -0.95
     Hopf
    -0.95
     avoient
    -0.95
     Chriftian
    -0.94
     greateſt
    -0.94
    POSITIVE LOGITS
     all
    0.92
     a
    0.91
     the
    0.88
     be
    0.87
     his
    0.84
     not
    0.83
     con
    0.81
     an
    0.80
     co
    0.80
     go
    0.80
    Act Density 1.023%

    No Known Activations