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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' professions and nationalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auen
    -0.17
    artz
    -0.15
    eil
    -0.15
    avir
    -0.15
    ecurity
    -0.15
    ej
    -0.15
    Current
    -0.15
    agner
    -0.15
    313
    -0.14
    terra
    -0.14
    POSITIVE LOGITS
     states
    0.31
     polym
    0.27
    states
    0.25
    -states
    0.25
     bot
    0.25
     jur
    0.23
     politician
    0.23
     STATES
    0.22
     reform
    0.22
     States
    0.21
    Act Density 0.183%

    No Known Activations