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

    Neuronpedia

    INDEX
    Explanations

    references to company hiring practices and employment changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Truman
    -0.16
    ansi
    -0.15
     Reactive
    -0.15
    zcze
    -0.14
    cit
    -0.14
    krv
    -0.14
     Harper
    -0.14
     endors
    -0.14
    react
    -0.13
     endorsed
    -0.13
    POSITIVE LOGITS
     Model
    0.38
     Tesla
    0.36
     tes
    0.33
     Tes
    0.31
    Tesla
    0.29
     EV
    0.29
    Model
    0.29
    Tes
    0.27
     MODEL
    0.26
     Musk
    0.25
    Act Density 0.023%

    No Known Activations