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

    Neuronpedia

    INDEX
    Explanations

    question phrases and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antMatchers
    -0.99
     Hesper
    -0.86
     Astra
    -0.85
     trx
    -0.84
     Grau
    -0.79
    HomeAsUpEnabled
    -0.78
     Onyx
    -0.78
     Houſe
    -0.78
     Hift
    -0.77
     Leinster
    -0.77
    POSITIVE LOGITS
     did
    1.04
     DID
    1.00
    did
    0.93
     Did
    0.88
     went
    0.81
     took
    0.81
     came
    0.81
     didn
    0.80
    DID
    0.80
     had
    0.76
    Act Density 0.089%

    No Known Activations