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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and financial claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ugl
    -0.17
    alle
    -0.16
    uet
    -0.15
    ikh
    -0.15
    andin
    -0.15
    udic
    -0.15
     stupid
    -0.15
    chimp
    -0.14
    uder
    -0.14
    atar
    -0.14
    POSITIVE LOGITS
     suspect
    0.27
     fatally
    0.22
     faulty
    0.21
     sketch
    0.21
     flawed
    0.21
     defective
    0.20
    fault
    0.19
     Fault
    0.19
     fall
    0.18
     bere
    0.17
    Act Density 0.167%

    No Known Activations