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

    Neuronpedia

    INDEX
    Explanations

    references to political appointments and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Evange
    -0.46
    UED
    -0.46
     fas
    -0.42
    nEnter
    -0.42
     copy
    -0.41
     折
    -0.41
    laga
    -0.41
     morg
    -0.40
    pses
    -0.40
    llog
    -0.40
    POSITIVE LOGITS
     betweenstory
    0.93
     appointing
    0.86
     appoint
    0.77
     appointed
    0.74
    @[+][
    0.74
     appoints
    0.73
    appointed
    0.72
    RegistryLite
    0.72
    twimg
    0.71
     appointment
    0.71
    Act Density 0.382%

    No Known Activations