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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "got" and its variations or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.12
     itſelf
    -1.11
     themſelves
    -1.02
    ſelf
    -1.00
     ſtate
    -0.98
    ſelves
    -0.98
     houſe
    -0.97
     neceff
    -0.97
     Houſe
    -0.97
     Reſ
    -0.96
    POSITIVE LOGITS
     rid
    1.09
     a
    1.02
     into
    0.86
     an
    0.84
     caught
    0.79
     to
    0.76
     the
    0.76
     stuck
    0.73
     it
    0.71
     some
    0.70
    Act Density 0.113%

    No Known Activations