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

    Neuronpedia

    INDEX
    Explanations

    information related to government investigations and political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.31
     himſelf
    -1.17
     raiſ
    -1.16
     purpoſe
    -1.15
     pleaſure
    -1.08
     poffible
    -1.04
     themſelves
    -1.02
     uſed
    -1.01
     ſtate
    -1.00
     houſe
    -1.00
    POSITIVE LOGITS
     to
    0.59
     for
    0.56
     in
    0.55
     at
    0.52
     on
    0.51
     się
    0.48
     by
    0.46
     à
    0.45
     dét
    0.44
     as
    0.44
    Act Density 0.496%

    No Known Activations