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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references to jury instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prefixer
    -0.64
     currently
    -0.61
     attualmente
    -0.60
    İstinadlar
    -0.60
    昔から
    -0.59
    middels
    -0.59
     atualmente
    -0.59
    tualmente
    -0.58
     derzeit
    -0.56
     Actualmente
    -0.56
    POSITIVE LOGITS
     was
    0.85
     did
    0.83
     wore
    0.78
     didn
    0.78
     went
    0.78
     wasn
    0.77
     Wasn
    0.74
    did
    0.73
     gave
    0.73
    Did
    0.73
    Act Density 0.796%

    No Known Activations