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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "did" and phrases involving negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antMatchers
    -0.92
    Composable
    -0.89
    HCR
    -0.79
     actuels
    -0.78
    Poss
    -0.78
     Possession
    -0.77
     actuelles
    -0.75
     Sambo
    -0.74
     viață
    -0.74
    NOPQRST
    -0.73
    POSITIVE LOGITS
     did
    1.11
     DID
    1.11
     Did
    0.99
    did
    0.96
    DID
    0.92
     Didi
    0.84
     didn
    0.83
     had
    0.82
    Did
    0.79
    었
    0.78
    Act Density 0.130%

    No Known Activations