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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding the concept of crime decline and its validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bias
    -0.14
    Aspect
    -0.14
    plus
    -0.14
     Pok
    -0.14
    enko
    -0.13
     Sent
    -0.13
    expl
    -0.13
    eki
    -0.13
    sink
    -0.13
    ModelProperty
    -0.13
    POSITIVE LOGITS
     disc
    0.21
     prem
    0.20
     contest
    0.19
     legit
    0.19
     circ
    0.18
     reproduced
    0.18
    located
    0.18
     mobil
    0.17
    iminal
    0.17
     understood
    0.17
    Act Density 0.203%

    No Known Activations