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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and financial interests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DNEY
    -0.71
    scriptcase
    -0.71
    izop
    -0.70
    ophanes
    -0.67
     Dumas
    -0.65
     Faber
    -0.63
     Bradshaw
    -0.62
     spake
    -0.62
    Rox
    -0.62
     Vaticano
    -0.62
    POSITIVE LOGITS
     interest
    1.88
     Interest
    1.87
     interests
    1.85
    Interest
    1.77
     Interests
    1.73
     INTEREST
    1.73
    interest
    1.68
    INTEREST
    1.58
    Interests
    1.52
    interests
    1.44
    Act Density 0.050%

    No Known Activations