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

    Neuronpedia

    INDEX
    Explanations

    words related to "flags" and "joint."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     réussir
    -0.47
     للمعارف
    -0.46
     testimonial
    -0.43
    tênis
    -0.43
    wohnungen
    -0.43
     miniaturka
    -0.42
    remoto
    -0.41
     dormitórios
    -0.41
     Jeffries
    -0.41
     productivity
    -0.40
    POSITIVE LOGITS
     flags
    1.07
     flew
    0.94
     flying
    0.94
     Flags
    0.90
     flown
    0.90
     Joint
    0.88
    Flags
    0.87
     joint
    0.86
     Flying
    0.82
     flag
    0.81
    Act Density 0.191%

    No Known Activations